Search Results for author: Yang song

Found 181 papers, 95 papers with code

Improved Word Sense Disambiguation with Enhanced Sense Representations

1 code implementation Findings (EMNLP) 2021 Yang song, Xin Cai Ong, Hwee Tou Ng, Qian Lin

Current state-of-the-art supervised word sense disambiguation (WSD) systems (such as GlossBERT and bi-encoder model) yield surprisingly good results by purely leveraging pre-trained language models and short dictionary definitions (or glosses) of the different word senses.

Word Sense Disambiguation

E-ConvRec: A Large-Scale Conversational Recommendation Dataset for E-Commerce Customer Service

no code implementations LREC 2022 Meihuizi Jia, Ruixue Liu, Peiying Wang, Yang song, Zexi Xi, Haobin Li, Xin Shen, Meng Chen, Jinhui Pang, Xiaodong He

There has been a growing interest in developing conversational recommendation system (CRS), which provides valuable recommendations to users through conversations.

Dialogue Management Management

Large Language Models Enhanced Collaborative Filtering

no code implementations26 Mar 2024 Zhongxiang Sun, Zihua Si, Xiaoxue Zang, Kai Zheng, Yang song, Xiao Zhang, Jun Xu

In this paper, drawing inspiration from the in-context learning and chain of thought reasoning in LLMs, we propose the Large Language Models enhanced Collaborative Filtering (LLM-CF) framework, which distils the world knowledge and reasoning capabilities of LLMs into collaborative filtering.

Collaborative Filtering In-Context Learning +2

Inter- and intra-uncertainty based feature aggregation model for semi-supervised histopathology image segmentation

1 code implementation19 Mar 2024 Qiangguo Jin, Hui Cui, Changming Sun, Yang song, Jiangbin Zheng, Leilei Cao, Leyi Wei, Ran Su

To address these issues, we first propose a novel inter- and intra-uncertainty regularization method to measure and constrain both inter- and intra-inconsistencies in the teacher-student architecture.

Image Segmentation Semantic Segmentation

Towards Effective Usage of Human-Centric Priors in Diffusion Models for Text-based Human Image Generation

no code implementations8 Mar 2024 Junyan Wang, Zhenhong Sun, Zhiyu Tan, Xuanbai Chen, Weihua Chen, Hao Li, Cheng Zhang, Yang song

Vanilla text-to-image diffusion models struggle with generating accurate human images, commonly resulting in imperfect anatomies such as unnatural postures or disproportionate limbs. Existing methods address this issue mostly by fine-tuning the model with extra images or adding additional controls -- human-centric priors such as pose or depth maps -- during the image generation phase.

Image Generation

The 2nd Workshop on Recommendation with Generative Models

no code implementations7 Mar 2024 Wenjie Wang, Yang Zhang, Xinyu Lin, Fuli Feng, Weiwen Liu, Yong liu, Xiangyu Zhao, Wayne Xin Zhao, Yang song, Xiangnan He

The rise of generative models has driven significant advancements in recommender systems, leaving unique opportunities for enhancing users' personalized recommendations.

Recommendation Systems

A Holistic Power Optimization Approach for Microgrid Control Based on Deep Reinforcement Learning

no code implementations1 Mar 2024 Fulong Yao, Wanqing Zhao, Matthew Forshaw, Yang song

The global energy landscape is undergoing a transformation towards decarbonization, sustainability, and cost-efficiency.

energy management

KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph

no code implementations17 Feb 2024 Jinhao Jiang, Kun Zhou, Wayne Xin Zhao, Yang song, Chen Zhu, HengShu Zhu, Ji-Rong Wen

To guarantee the effectiveness, we leverage program language to formulate the multi-hop reasoning process over the KG, and synthesize a code-based instruction dataset to fine-tune the base LLM.

Knowledge Graphs

Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization

1 code implementation5 Feb 2024 Yang Jin, Zhicheng Sun, Kun Xu, Liwei Chen, Hao Jiang, Quzhe Huang, Chengru Song, Yuliang Liu, Di Zhang, Yang song, Kun Gai, Yadong Mu

In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos.

Video Understanding Visual Question Answering

Coupling Graph Neural Networks with Fractional Order Continuous Dynamics: A Robustness Study

no code implementations9 Jan 2024 Qiyu Kang, Kai Zhao, Yang song, Yihang Xie, Yanan Zhao, Sijie Wang, Rui She, Wee Peng Tay

In this work, we rigorously investigate the robustness of graph neural fractional-order differential equation (FDE) models.

PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations

no code implementations6 Jan 2024 Rui She, Sijie Wang, Qiyu Kang, Kai Zhao, Yang song, Wee Peng Tay, Tianyu Geng, Xingchao Jian

We leverage a graph neural partial differential equation (PDE) based on Beltrami flow to obtain high-dimensional features and position embeddings for point clouds.

Point Cloud Registration Position

LabelCraft: Empowering Short Video Recommendations with Automated Label Crafting

1 code implementation18 Dec 2023 Yimeng Bai, Yang Zhang, Jing Lu, Jianxin Chang, Xiaoxue Zang, Yanan Niu, Yang song, Fuli Feng

Through meta-learning techniques, LabelCraft effectively addresses the bi-level optimization hurdle posed by the recommender and labeling models, enabling the automatic acquisition of intricate label generation mechanisms. Extensive experiments on real-world datasets corroborate LabelCraft's excellence across varied operational metrics, encompassing usage time, user engagement, and retention.

Meta-Learning Model Optimization

DistilVPR: Cross-Modal Knowledge Distillation for Visual Place Recognition

1 code implementation17 Dec 2023 Sijie Wang, Rui She, Qiyu Kang, Xingchao Jian, Kai Zhao, Yang song, Wee Peng Tay

The utilization of multi-modal sensor data in visual place recognition (VPR) has demonstrated enhanced performance compared to single-modal counterparts.

Knowledge Distillation Visual Place Recognition

DARNet: Bridging Domain Gaps in Cross-Domain Few-Shot Segmentation with Dynamic Adaptation

no code implementations8 Dec 2023 Haoran Fan, Qi Fan, Maurice Pagnucco, Yang song

Moreover, recognizing the variability across target domains, an Adaptive Refine Self-Matching (ARSM) method is also proposed to adjust the matching threshold and dynamically refine the prediction result with the self-matching method, enhancing accuracy.

Cross-Domain Few-Shot Segmentation +2

An annotated grain kernel image database for visual quality inspection

2 code implementations20 Nov 2023 Lei Fan, Yiwen Ding, Dongdong Fan, Yong Wu, Hongxia Chu, Maurice Pagnucco, Yang song

We present a machine vision-based database named GrainSet for the purpose of visual quality inspection of grain kernels.

Inverse Learning with Extremely Sparse Feedback for Recommendation

1 code implementation14 Nov 2023 GuanYu Lin, Chen Gao, Yu Zheng, Yinfeng Li, Jianxin Chang, Yanan Niu, Yang song, Kun Gai, Zhiheng Li, Depeng Jin, Yong Li

In this paper, we propose a meta-learning method to annotate the unlabeled data from loss and gradient perspectives, which considers the noises in both positive and negative instances.

Meta-Learning

Mixed Attention Network for Cross-domain Sequential Recommendation

1 code implementation14 Nov 2023 GuanYu Lin, Chen Gao, Yu Zheng, Jianxin Chang, Yanan Niu, Yang song, Kun Gai, Zhiheng Li, Depeng Jin, Yong Li, Meng Wang

Recent proposed cross-domain sequential recommendation models such as PiNet and DASL have a common drawback relying heavily on overlapped users in different domains, which limits their usage in practical recommender systems.

Sequential Recommendation

Bridging the Information Gap Between Domain-Specific Model and General LLM for Personalized Recommendation

no code implementations7 Nov 2023 Wenxuan Zhang, Hongzhi Liu, Yingpeng Du, Chen Zhu, Yang song, HengShu Zhu, Zhonghai Wu

Nevertheless, these methods encounter the certain issue that information such as community behavior pattern in RS domain is challenging to express in natural language, which limits the capability of LLMs to surpass state-of-the-art domain-specific models.

RobustMat: Neural Diffusion for Street Landmark Patch Matching under Challenging Environments

1 code implementation7 Nov 2023 Rui She, Qiyu Kang, Sijie Wang, Yuan-Rui Yang, Kai Zhao, Yang song, Wee Peng Tay

For autonomous vehicles (AVs), visual perception techniques based on sensors like cameras play crucial roles in information acquisition and processing.

Autonomous Vehicles Patch Matching

Improved Techniques for Training Consistency Models

2 code implementations22 Oct 2023 Yang song, Prafulla Dhariwal

Consistency models are a nascent family of generative models that can sample high quality data in one step without the need for adversarial training.

Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach

1 code implementation NeurIPS 2023 Kai Zhao, Qiyu Kang, Yang song, Rui She, Sijie Wang, Wee Peng Tay

Graph neural networks (GNNs) are vulnerable to adversarial perturbations, including those that affect both node features and graph topology.

Adversarial Robustness

A Marketplace Price Anomaly Detection System at Scale

no code implementations6 Oct 2023 Akshit Sarpal, Qiwen Kang, Fangping Huang, Yang song, Lijie Wan

Lack of centralized guardrails that are available for a traditional online retailer causes a higher likelihood for inaccurate prices to get published on the website, leading to poor customer experience and potential for revenue loss.

Anomaly Detection

Generative Retrieval with Semantic Tree-Structured Item Identifiers via Contrastive Learning

no code implementations23 Sep 2023 Zihua Si, Zhongxiang Sun, Jiale Chen, Guozhang Chen, Xiaoxue Zang, Kai Zheng, Yang song, Xiao Zhang, Jun Xu

To obtain efficiency and effectiveness, this paper introduces a generative retrieval framework, namely SEATER, which learns SEmAntic Tree-structured item identifiERs via contrastive learning.

Contrastive Learning Recommendation Systems +1

Speech-Gesture GAN: Gesture Generation for Robots and Embodied Agents

no code implementations17 Sep 2023 Carson Yu Liu, Gelareh Mohammadi, Yang song, Wafa Johal

In order to train our neural network model, we employ a public dataset containing co-speech gestures with corresponding speech audio utterances, which were captured from a single male native English speaker.

Generative Adversarial Network Gesture Generation

Learning and Optimization of Implicit Negative Feedback for Industrial Short-video Recommender System

no code implementations25 Aug 2023 Yunzhu Pan, Nian Li, Chen Gao, Jianxin Chang, Yanan Niu, Yang song, Depeng Jin, Yong Li

Specifically, in short-video recommendation, the easiest-to-collect user feedback is the skipping behavior, which leads to two critical challenges for the recommendation model.

Recommendation Systems

Generalizable Zero-Shot Speaker Adaptive Speech Synthesis with Disentangled Representations

no code implementations24 Aug 2023 Wenbin Wang, Yang song, Sanjay Jha

However, most current approaches suffer from the degradation of naturalness and speaker similarity when synthesizing speech for unseen speakers (i. e., speakers not in the training dataset) due to the poor generalizability of the model in out-of-distribution data.

Representation Learning Speech Synthesis +1

SHARK: A Lightweight Model Compression Approach for Large-scale Recommender Systems

no code implementations18 Aug 2023 Beichuan Zhang, Chenggen Sun, Jianchao Tan, Xinjun Cai, Jun Zhao, Mengqi Miao, Kang Yin, Chengru Song, Na Mou, Yang song

Increasing the size of embedding layers has shown to be effective in improving the performance of recommendation models, yet gradually causing their sizes to exceed terabytes in industrial recommender systems, and hence the increase of computing and storage costs.

Model Compression Quantization +1

Understanding and Modeling Passive-Negative Feedback for Short-video Sequential Recommendation

no code implementations8 Aug 2023 Yunzhu Pan, Chen Gao, Jianxin Chang, Yanan Niu, Yang song, Kun Gai, Depeng Jin, Yong Li

To enhance the robustness of our model, we then introduce a multi-task learning module to simultaneously optimize two kinds of feedback -- passive-negative feedback and traditional randomly-sampled negative feedback.

Multi-Task Learning Sequential Recommendation

Graph Contrastive Learning with Generative Adversarial Network

no code implementations1 Aug 2023 Cheng Wu, Chaokun Wang, Jingcao Xu, Ziyang Liu, Kai Zheng, Xiaowei Wang, Yang song, Kun Gai

Specifically, we present GACN, a novel Generative Adversarial Contrastive learning Network for graph representation learning.

Contrastive Learning Data Augmentation +3

Enhancing Job Recommendation through LLM-based Generative Adversarial Networks

no code implementations20 Jul 2023 Yingpeng Du, Di Luo, Rui Yan, Hongzhi Liu, Yang song, HengShu Zhu, Jie Zhang

However, directly leveraging LLMs to enhance recommendation results is not a one-size-fits-all solution, as LLMs may suffer from fabricated generation and few-shot problems, which degrade the quality of resume completion.

TractGeoNet: A geometric deep learning framework for pointwise analysis of tract microstructure to predict language assessment performance

no code implementations8 Jul 2023 Yuqian Chen, Leo R. Zekelman, Chaoyi Zhang, Tengfei Xue, Yang song, Nikos Makris, Yogesh Rathi, Alexandra J. Golby, Weidong Cai, Fan Zhang, Lauren J. O'Donnell

We evaluate the effectiveness of the proposed method by predicting individual performance on two neuropsychological assessments of language using a dataset of 20 association white matter fiber tracts from 806 subjects from the Human Connectome Project.

regression

SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generation

1 code implementation4 Jul 2023 Qi Yan, Zhengyang Liang, Yang song, Renjie Liao, Lele Wang

Diffusion models based on permutation-equivariant networks can learn permutation-invariant distributions for graph data.

Denoising Graph Generation

Reciprocal Sequential Recommendation

1 code implementation26 Jun 2023 Bowen Zheng, Yupeng Hou, Wayne Xin Zhao, Yang song, HengShu Zhu

Existing RRS models mainly capture static user preferences, which have neglected the evolving user tastes and the dynamic matching relation between the two parties.

Sequential Recommendation

KuaiSAR: A Unified Search And Recommendation Dataset

no code implementations13 Jun 2023 Zhongxiang Sun, Zihua Si, Xiaoxue Zang, Dewei Leng, Yanan Niu, Yang song, Xiao Zhang, Jun Xu

We believe this dataset will serve as a catalyst for innovative research and bridge the gap between academia and industry in understanding the S&R services in practical, real-world applications.

Multi-Task Learning Recommendation Systems

PANE-GNN: Unifying Positive and Negative Edges in Graph Neural Networks for Recommendation

no code implementations7 Jun 2023 Ziyang Liu, Chaokun Wang, Jingcao Xu, Cheng Wu, Kai Zheng, Yang song, Na Mou, Kun Gai

Recommender systems play a crucial role in addressing the issue of information overload by delivering personalized recommendations to users.

Denoising Graph Representation Learning +1

Node Embedding from Neural Hamiltonian Orbits in Graph Neural Networks

1 code implementation30 May 2023 Qiyu Kang, Kai Zhao, Yang song, Sijie Wang, Wee Peng Tay

In the graph node embedding problem, embedding spaces can vary significantly for different data types, leading to the need for different GNN model types.

Graph Embedding Link Prediction +1

Graph Neural Convection-Diffusion with Heterophily

1 code implementation26 May 2023 Kai Zhao, Qiyu Kang, Yang song, Rui She, Sijie Wang, Wee Peng Tay

Graph neural networks (GNNs) have shown promising results across various graph learning tasks, but they often assume homophily, which can result in poor performance on heterophilic graphs.

Graph Learning Node Classification

Instant Representation Learning for Recommendation over Large Dynamic Graphs

1 code implementation22 May 2023 Cheng Wu, Chaokun Wang, Jingcao Xu, Ziwei Fang, Tiankai Gu, Changping Wang, Yang song, Kai Zheng, Xiaowei Wang, Guorui Zhou

Furthermore, the Neighborhood Disturbance existing in dynamic graphs deteriorates the performance of neighbor-aggregation based graph models.

Recommendation Systems Representation Learning

Multi-behavior Self-supervised Learning for Recommendation

1 code implementation22 May 2023 Jingcao Xu, Chaokun Wang, Cheng Wu, Yang song, Kai Zheng, Xiaowei Wang, Changping Wang, Guorui Zhou, Kun Gai

Secondly, existing methods utilizing self-supervised learning (SSL) to tackle the data sparsity neglect the serious optimization imbalance between the SSL task and the target task.

Recommendation Systems Self-Supervised Learning

When Search Meets Recommendation: Learning Disentangled Search Representation for Recommendation

1 code implementation18 May 2023 Zihua Si, Zhongxiang Sun, Xiao Zhang, Jun Xu, Xiaoxue Zang, Yang song, Kun Gai, Ji-Rong Wen

In our paper, we propose a Search-Enhanced framework for the Sequential Recommendation (SESRec) that leverages users' search interests for recommendation, by disentangling similar and dissimilar representations within S&R behaviors.

Contrastive Learning Disentanglement +1

GPT-4 Technical Report

9 code implementations Preprint 2023 OpenAI, :, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, Irwan Bello, Jake Berdine, Gabriel Bernadett-Shapiro, Christopher Berner, Lenny Bogdonoff, Oleg Boiko, Madelaine Boyd, Anna-Luisa Brakman, Greg Brockman, Tim Brooks, Miles Brundage, Kevin Button, Trevor Cai, Rosie Campbell, Andrew Cann, Brittany Carey, Chelsea Carlson, Rory Carmichael, Brooke Chan, Che Chang, Fotis Chantzis, Derek Chen, Sully Chen, Ruby Chen, Jason Chen, Mark Chen, Ben Chess, Chester Cho, Casey Chu, Hyung Won Chung, Dave Cummings, Jeremiah Currier, Yunxing Dai, Cory Decareaux, Thomas Degry, Noah Deutsch, Damien Deville, Arka Dhar, David Dohan, Steve Dowling, Sheila Dunning, Adrien Ecoffet, Atty Eleti, Tyna Eloundou, David Farhi, Liam Fedus, Niko Felix, Simón Posada Fishman, Juston Forte, Isabella Fulford, Leo Gao, Elie Georges, Christian Gibson, Vik Goel, Tarun Gogineni, Gabriel Goh, Rapha Gontijo-Lopes, Jonathan Gordon, Morgan Grafstein, Scott Gray, Ryan Greene, Joshua Gross, Shixiang Shane Gu, Yufei Guo, Chris Hallacy, Jesse Han, Jeff Harris, Yuchen He, Mike Heaton, Johannes Heidecke, Chris Hesse, Alan Hickey, Wade Hickey, Peter Hoeschele, Brandon Houghton, Kenny Hsu, Shengli Hu, Xin Hu, Joost Huizinga, Shantanu Jain, Shawn Jain, Joanne Jang, Angela Jiang, Roger Jiang, Haozhun Jin, Denny Jin, Shino Jomoto, Billie Jonn, Heewoo Jun, Tomer Kaftan, Łukasz Kaiser, Ali Kamali, Ingmar Kanitscheider, Nitish Shirish Keskar, Tabarak Khan, Logan Kilpatrick, Jong Wook Kim, Christina Kim, Yongjik Kim, Jan Hendrik Kirchner, Jamie Kiros, Matt Knight, Daniel Kokotajlo, Łukasz Kondraciuk, Andrew Kondrich, Aris Konstantinidis, Kyle Kosic, Gretchen Krueger, Vishal Kuo, Michael Lampe, Ikai Lan, Teddy Lee, Jan Leike, Jade Leung, Daniel Levy, Chak Ming Li, Rachel Lim, Molly Lin, Stephanie Lin, Mateusz Litwin, Theresa Lopez, Ryan Lowe, Patricia Lue, Anna Makanju, Kim Malfacini, Sam Manning, Todor Markov, Yaniv Markovski, Bianca Martin, Katie Mayer, Andrew Mayne, Bob McGrew, Scott Mayer McKinney, Christine McLeavey, Paul McMillan, Jake McNeil, David Medina, Aalok Mehta, Jacob Menick, Luke Metz, Andrey Mishchenko, Pamela Mishkin, Vinnie Monaco, Evan Morikawa, Daniel Mossing, Tong Mu, Mira Murati, Oleg Murk, David Mély, Ashvin Nair, Reiichiro Nakano, Rajeev Nayak, Arvind Neelakantan, Richard Ngo, Hyeonwoo Noh, Long Ouyang, Cullen O'Keefe, Jakub Pachocki, Alex Paino, Joe Palermo, Ashley Pantuliano, Giambattista Parascandolo, Joel Parish, Emy Parparita, Alex Passos, Mikhail Pavlov, Andrew Peng, Adam Perelman, Filipe de Avila Belbute Peres, Michael Petrov, Henrique Ponde de Oliveira Pinto, Michael, Pokorny, Michelle Pokrass, Vitchyr H. Pong, Tolly Powell, Alethea Power, Boris Power, Elizabeth Proehl, Raul Puri, Alec Radford, Jack Rae, Aditya Ramesh, Cameron Raymond, Francis Real, Kendra Rimbach, Carl Ross, Bob Rotsted, Henri Roussez, Nick Ryder, Mario Saltarelli, Ted Sanders, Shibani Santurkar, Girish Sastry, Heather Schmidt, David Schnurr, John Schulman, Daniel Selsam, Kyla Sheppard, Toki Sherbakov, Jessica Shieh, Sarah Shoker, Pranav Shyam, Szymon Sidor, Eric Sigler, Maddie Simens, Jordan Sitkin, Katarina Slama, Ian Sohl, Benjamin Sokolowsky, Yang song, Natalie Staudacher, Felipe Petroski Such, Natalie Summers, Ilya Sutskever, Jie Tang, Nikolas Tezak, Madeleine B. Thompson, Phil Tillet, Amin Tootoonchian, Elizabeth Tseng, Preston Tuggle, Nick Turley, Jerry Tworek, Juan Felipe Cerón Uribe, Andrea Vallone, Arun Vijayvergiya, Chelsea Voss, Carroll Wainwright, Justin Jay Wang, Alvin Wang, Ben Wang, Jonathan Ward, Jason Wei, CJ Weinmann, Akila Welihinda, Peter Welinder, Jiayi Weng, Lilian Weng, Matt Wiethoff, Dave Willner, Clemens Winter, Samuel Wolrich, Hannah Wong, Lauren Workman, Sherwin Wu, Jeff Wu, Michael Wu, Kai Xiao, Tao Xu, Sarah Yoo, Kevin Yu, Qiming Yuan, Wojciech Zaremba, Rowan Zellers, Chong Zhang, Marvin Zhang, Shengjia Zhao, Tianhao Zheng, Juntang Zhuang, William Zhuk, Barret Zoph

We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs.

 Ranked #1 on Only Connect Walls Dataset Task 1 (Grouping) on OCW (using extra training data)

Arithmetic Reasoning Bug fixing +9

Hybrid Dual Mean-Teacher Network With Double-Uncertainty Guidance for Semi-Supervised Segmentation of MRI Scans

1 code implementation9 Mar 2023 JiaYi Zhu, Bart Bolsterlee, Brian V. Y. Chow, Yang song, Erik Meijering

We then propose a hybrid regularization module to encourage both student models to produce results close to the uncertainty-weighted hybrid prediction.

Image Segmentation Medical Image Segmentation +3

Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition

1 code implementation5 Mar 2023 Junyan Wang, Zhenhong Sun, Yichen Qian, Dong Gong, Xiuyu Sun, Ming Lin, Maurice Pagnucco, Yang song

In this work, we propose to automatically design efficient 3D CNN architectures via a novel training-free neural architecture search approach tailored for 3D CNNs considering the model complexity.

Action Recognition Computational Efficiency +2

Consistency Models

8 code implementations2 Mar 2023 Yang song, Prafulla Dhariwal, Mark Chen, Ilya Sutskever

Through extensive experiments, we demonstrate that they outperform existing distillation techniques for diffusion models in one- and few-step sampling, achieving the new state-of-the-art FID of 3. 55 on CIFAR-10 and 6. 20 on ImageNet 64x64 for one-step generation.

Colorization Image Inpainting +2

Node Embedding from Hamiltonian Information Propagation in Graph Neural Networks

no code implementations2 Mar 2023 Qiyu Kang, Kai Zhao, Yang song, Sijie Wang, Rui She, Wee Peng Tay

Graph neural networks (GNNs) have achieved success in various inference tasks on graph-structured data.

Multimodal Trajectory Prediction: A Survey

no code implementations21 Feb 2023 Renhao Huang, Hao Xue, Maurice Pagnucco, Flora Salim, Yang song

Trajectory prediction is an important task to support safe and intelligent behaviours in autonomous systems.

Trajectory Prediction

Dual-interest Factorization-heads Attention for Sequential Recommendation

1 code implementation8 Feb 2023 GuanYu Lin, Chen Gao, Yu Zheng, Jianxin Chang, Yanan Niu, Yang song, Zhiheng Li, Depeng Jin, Yong Li

In this paper, we propose Dual-interest Factorization-heads Attention for Sequential Recommendation (short for DFAR) consisting of feedback-aware encoding layer, dual-interest disentangling layer and prediction layer.

Disentanglement Sequential Recommendation

TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou

no code implementations5 Feb 2023 Jianxin Chang, Chenbin Zhang, Zhiyi Fu, Xiaoxue Zang, Lin Guan, Jing Lu, Yiqun Hui, Dewei Leng, Yanan Niu, Yang song, Kun Gai

And for the user-item cross features, we compress each into a one-dimentional bias term in the attention score calculation to save the computational cost.

Click-Through Rate Prediction

PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Information

1 code implementation2 Feb 2023 Jianxin Chang, Chenbin Zhang, Yiqun Hui, Dewei Leng, Yanan Niu, Yang song, Kun Gai

By infusing personalized selection of Embedding and personalized modification of DNN parameters, PEPNet tailored to the interests of each individual obtains significant performance gains, with online improvements exceeding 1\% in multiple task metrics across multiple domains.

Recommendation Systems

TractGraphCNN: anatomically informed graph CNN for classification using diffusion MRI tractography

no code implementations5 Jan 2023 Yuqian Chen, Fan Zhang, Leo R. Zekelman, Tengfei Xue, Chaoyi Zhang, Yang song, Nikos Makris, Yogesh Rathi, Weidong Cai, Lauren J. O'Donnell

This work shows the potential of incorporating anatomical information, especially known anatomical similarities between input features, to guide convolutions in neural networks.

EZInterviewer: To Improve Job Interview Performance with Mock Interview Generator

no code implementations3 Jan 2023 Mingzhe Li, Xiuying Chen, Weiheng Liao, Yang song, Tao Zhang, Dongyan Zhao, Rui Yan

The key idea is to reduce the number of parameters that rely on interview dialogs by disentangling the knowledge selector and dialog generator so that most parameters can be trained with ungrounded dialogs as well as the resume data that are not low-resource.

1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results

no code implementations24 Nov 2022 Benjamin Kiefer, Matej Kristan, Janez Perš, Lojze Žust, Fabio Poiesi, Fabio Augusto de Alcantara Andrade, Alexandre Bernardino, Matthew Dawkins, Jenni Raitoharju, Yitong Quan, Adem Atmaca, Timon Höfer, Qiming Zhang, Yufei Xu, Jing Zhang, DaCheng Tao, Lars Sommer, Raphael Spraul, Hangyue Zhao, Hongpu Zhang, Yanyun Zhao, Jan Lukas Augustin, Eui-ik Jeon, Impyeong Lee, Luca Zedda, Andrea Loddo, Cecilia Di Ruberto, Sagar Verma, Siddharth Gupta, Shishir Muralidhara, Niharika Hegde, Daitao Xing, Nikolaos Evangeliou, Anthony Tzes, Vojtěch Bartl, Jakub Špaňhel, Adam Herout, Neelanjan Bhowmik, Toby P. Breckon, Shivanand Kundargi, Tejas Anvekar, Chaitra Desai, Ramesh Ashok Tabib, Uma Mudengudi, Arpita Vats, Yang song, Delong Liu, Yonglin Li, Shuman Li, Chenhao Tan, Long Lan, Vladimir Somers, Christophe De Vleeschouwer, Alexandre Alahi, Hsiang-Wei Huang, Cheng-Yen Yang, Jenq-Neng Hwang, Pyong-Kun Kim, Kwangju Kim, Kyoungoh Lee, Shuai Jiang, Haiwen Li, Zheng Ziqiang, Tuan-Anh Vu, Hai Nguyen-Truong, Sai-Kit Yeung, Zhuang Jia, Sophia Yang, Chih-Chung Hsu, Xiu-Yu Hou, Yu-An Jhang, Simon Yang, Mau-Tsuen Yang

The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection.

Object object-detection +2

Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training

1 code implementation21 Nov 2022 Ling Yang, Zhilin Huang, Yang song, Shenda Hong, Guohao Li, Wentao Zhang, Bin Cui, Bernard Ghanem, Ming-Hsuan Yang

Generating images from graph-structured inputs, such as scene graphs, is uniquely challenging due to the difficulty of aligning nodes and connections in graphs with objects and their relations in images.

Image Generation

Uncertainty Sentence Sampling by Virtual Adversarial Perturbation

no code implementations26 Oct 2022 Hanshan Zhang, Zhen Zhang, Hongfei Jiang, Yang song

Active learning for sentence understanding attempts to reduce the annotation cost by identifying the most informative examples.

Active Learning Sentence +1

AutoLV: Automatic Lecture Video Generator

no code implementations19 Sep 2022 Wenbin Wang, Yang song, Sanjay Jha

We propose an end-to-end lecture video generation system that can generate realistic and complete lecture videos directly from annotated slides, instructor's reference voice and instructor's reference portrait video.

Speech Synthesis Talking Head Generation +1

On the Robustness of Graph Neural Diffusion to Topology Perturbations

1 code implementation16 Sep 2022 Yang song, Qiyu Kang, Sijie Wang, Zhao Kai, Wee Peng Tay

In this work, we explore the robustness properties of graph neural PDEs.

Diffusion Models: A Comprehensive Survey of Methods and Applications

2 code implementations2 Sep 2022 Ling Yang, Zhilong Zhang, Yang song, Shenda Hong, Runsheng Xu, Yue Zhao, Yingxia Shao, Wentao Zhang, Bin Cui, Ming-Hsuan Yang

This survey aims to provide a contextualized, in-depth look at the state of diffusion models, identifying the key areas of focus and pointing to potential areas for further exploration.

Image Super-Resolution Text-to-Image Generation +1

Billion-user Customer Lifetime Value Prediction: An Industrial-scale Solution from Kuaishou

no code implementations29 Aug 2022 Kunpeng Li, Guangcui Shao, Naijun Yang, Xiao Fang, Yang song

Customer Life Time Value (LTV) is the expected total revenue that a single user can bring to a business.

Value prediction

Modeling Two-Way Selection Preference for Person-Job Fit

1 code implementation18 Aug 2022 Chen Yang, Yupeng Hou, Yang song, Tao Zhang, Ji-Rong Wen, Wayne Xin Zhao

To model the two-way selection preference from the dual-perspective of job seekers and employers, we incorporate two different nodes for each candidate (or job) and characterize both successful matching and failed matching via a unified dual-perspective interaction graph.

Contrastive Learning Graph Representation Learning +1

HybridGNN: Learning Hybrid Representation in Multiplex Heterogeneous Networks

no code implementations3 Aug 2022 Tiankai Gu, Chaokun Wang, Cheng Wu, Jingcao Xu, Yunkai Lou, Changping Wang, Kai Xu, Can Ye, Yang song

One of the most important tasks in recommender systems is to predict the potential connection between two nodes under a specific edge type (i. e., relationship).

Recommendation Systems

White Matter Tracts are Point Clouds: Neuropsychological Score Prediction and Critical Region Localization via Geometric Deep Learning

no code implementations6 Jul 2022 Yuqian Chen, Fan Zhang, Chaoyi Zhang, Tengfei Xue, Leo R. Zekelman, Jianzhong He, Yang song, Nikos Makris, Yogesh Rathi, Alexandra J. Golby, Weidong Cai, Lauren J. O'Donnell

In this paper, we propose a deep-learning-based framework for neuropsychological score prediction using microstructure measurements estimated from diffusion magnetic resonance imaging (dMRI) tractography, focusing on predicting performance on a receptive vocabulary assessment task based on a critical fiber tract for language, the arcuate fasciculus (AF).

Graph-based Spatial Transformer with Memory Replay for Multi-future Pedestrian Trajectory Prediction

1 code implementation CVPR 2022 Lihuan Li, Maurice Pagnucco, Yang song

Pedestrian trajectory prediction is an essential and challenging task for a variety of real-life applications such as autonomous driving and robotic motion planning.

Autonomous Driving Future prediction +3

When Multi-Level Meets Multi-Interest: A Multi-Grained Neural Model for Sequential Recommendation

1 code implementation3 May 2022 Yu Tian, Jianxin Chang, Yannan Niu, Yang song, Chenliang Li

Specifically, multi-interest methods such as ComiRec and MIMN, focus on extracting different interests for a user by performing historical item clustering, while graph convolution methods including TGSRec and SURGE elect to refine user preferences based on multi-level correlations between historical items.

Sequential Recommendation

Deep fiber clustering: Anatomically informed fiber clustering with self-supervised deep learning for fast and effective tractography parcellation

1 code implementation2 May 2022 Yuqian Chen, Chaoyi Zhang, Tengfei Xue, Yang song, Nikos Makris, Yogesh Rathi, Weidong Cai, Fan Zhang, Lauren J. O'Donnell

In this work, we propose a novel deep learning framework for white matter fiber clustering, Deep Fiber Clustering (DFC), which solves the unsupervised clustering problem as a self-supervised learning task with a domain-specific pretext task to predict pairwise fiber distances.

Anatomy Clustering +3

Computer-Aided Extraction of Select MRI Markers of Cerebral Small Vessel Disease: A Systematic Review

no code implementations4 Apr 2022 Jiyang Jiang, Dadong Wang, Yang song, Perminder S. Sachdev, Wei Wen

Cerebral small vessel disease (CSVD) is a major vascular contributor to cognitive impairment in ageing, including dementias.

Transfer Learning

Leveraging Search History for Improving Person-Job Fit

no code implementations27 Mar 2022 Yupeng Hou, Xingyu Pan, Wayne Xin Zhao, Shuqing Bian, Yang song, Tao Zhang, Ji-Rong Wen

As the core technique of online recruitment platforms, person-job fit can improve hiring efficiency by accurately matching job positions with qualified candidates.

Text Matching

Explainability in Graph Neural Networks: An Experimental Survey

no code implementations17 Mar 2022 Peibo Li, Yixing Yang, Maurice Pagnucco, Yang song

Graph neural networks (GNNs) have been extensively developed for graph representation learning in various application domains.

Graph Representation Learning

Towards Bi-directional Skip Connections in Encoder-Decoder Architectures and Beyond

no code implementations11 Mar 2022 Tiange Xiang, Chaoyi Zhang, Xinyi Wang, Yang song, Dongnan Liu, Heng Huang, Weidong Cai

With the backward skip connections, we propose a U-Net based network family, namely Bi-directional O-shape networks, which set new benchmarks on multiple public medical imaging segmentation datasets.

Medical Image Segmentation Neural Architecture Search +1

GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation

2 code implementations ICLR 2022 Minkai Xu, Lantao Yu, Yang song, Chence Shi, Stefano Ermon, Jian Tang

GeoDiff treats each atom as a particle and learns to directly reverse the diffusion process (i. e., transforming from a noise distribution to stable conformations) as a Markov chain.

Drug Discovery

StrongSORT: Make DeepSORT Great Again

14 code implementations28 Feb 2022 Yunhao Du, Zhicheng Zhao, Yang song, Yanyun Zhao, Fei Su, Tao Gong, Hongying Meng

As a result, the construction of a good baseline for a fair comparison is essential.

Ranked #6 on Multi-Object Tracking on MOT17 (using extra training data)

Multi-Object Tracking object-detection +1

A Model-Agnostic Causal Learning Framework for Recommendation using Search Data

1 code implementation9 Feb 2022 Zihua Si, Xueran Han, Xiao Zhang, Jun Xu, Yue Yin, Yang song, Ji-Rong Wen

In this paper, we propose a model-agnostic framework named IV4Rec that can effectively decompose the embedding vectors into these two parts, hence enhancing recommendation results.

Recommendation Systems

SupWMA: Consistent and Efficient Tractography Parcellation of Superficial White Matter with Deep Learning

1 code implementation29 Jan 2022 Tengfei Xue, Fan Zhang, Chaoyi Zhang, Yuqian Chen, Yang song, Nikos Makris, Yogesh Rathi, Weidong Cai, Lauren J. O'Donnell

Most parcellation methods focus on the deep white matter (DWM), while fewer methods address the superficial white matter (SWM) due to its complexity.

Contrastive Learning

Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement

1 code implementation6 Jan 2022 Dongnan Liu, Chaoyi Zhang, Yang song, Heng Huang, Chenyu Wang, Michael Barnett, Weidong Cai

Recent advances in unsupervised domain adaptation (UDA) techniques have witnessed great success in cross-domain computer vision tasks, enhancing the generalization ability of data-driven deep learning architectures by bridging the domain distribution gaps.

Disentanglement object-detection +2

Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving

no code implementations22 Dec 2021 Jingxiao Zheng, Xinwei Shi, Alexander Gorban, Junhua Mao, Yang song, Charles R. Qi, Ting Liu, Visesh Chari, Andre Cornman, Yin Zhou, CongCong Li, Dragomir Anguelov

3D human pose estimation (HPE) in autonomous vehicles (AV) differs from other use cases in many factors, including the 3D resolution and range of data, absence of dense depth maps, failure modes for LiDAR, relative location between the camera and LiDAR, and a high bar for estimation accuracy.

3D Human Pose Estimation Autonomous Driving

Density Ratio Estimation via Infinitesimal Classification

1 code implementation22 Nov 2021 Kristy Choi, Chenlin Meng, Yang song, Stefano Ermon

We then estimate the instantaneous rate of change of the bridge distributions indexed by time (the "time score") -- a quantity defined analogously to data (Stein) scores -- with a novel time score matching objective.

Classification Density Ratio Estimation +1

Solving Inverse Problems in Medical Imaging with Score-Based Generative Models

1 code implementation NeurIPS Workshop Deep_Invers 2021 Yang song, Liyue Shen, Lei Xing, Stefano Ermon

These measurements are typically synthesized from images using a fixed physical model of the measurement process, which hinders the generalization capability of models to unknown measurement processes.

Computed Tomography (CT)

Estimating High Order Gradients of the Data Distribution by Denoising

no code implementations NeurIPS 2021 Chenlin Meng, Yang song, Wenzhe Li, Stefano Ermon

By leveraging Tweedie's formula on higher order moments, we generalize denoising score matching to estimate higher order derivatives.

Audio Synthesis Denoising +2

Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks

2 code implementations NeurIPS 2021 Qiyu Kang, Yang song, Qinxu Ding, Wee Peng Tay

By ensuring that the equilibrium points of the ODE solution used as part of SODEF is Lyapunov-stable, the ODE solution for an input with a small perturbation converges to the same solution as the unperturbed input.

Score-Based Generative Classifiers

no code implementations1 Oct 2021 Roland S. Zimmermann, Lukas Schott, Yang song, Benjamin A. Dunn, David A. Klindt

In this work, we investigate score-based generative models as classifiers for natural images.

Classification

Concept-Aware Denoising Graph Neural Network for Micro-Video Recommendation

no code implementations28 Sep 2021 Yiyu Liu, Qian Liu, Yu Tian, Changping Wang, Yanan Niu, Yang song, Chenliang Li

In this paper, we propose a novel concept-aware denoising graph neural network (named CONDE) for micro-video recommendation.

Denoising Recommendation Systems

DSNet: A Dual-Stream Framework for Weakly-Supervised Gigapixel Pathology Image Analysis

no code implementations13 Sep 2021 Tiange Xiang, Yang song, Chaoyi Zhang, Dongnan Liu, Mei Chen, Fan Zhang, Heng Huang, Lauren O'Donnell, Weidong Cai

With image-level labels only, patch-wise classification would be sub-optimal due to inconsistency between the patch appearance and image-level label.

Classification whole slide images

Voxel-wise Cross-Volume Representation Learning for 3D Neuron Reconstruction

no code implementations14 Aug 2021 Heng Wang, Chaoyi Zhang, Jianhui Yu, Yang song, SiQi Liu, Wojciech Chrzanowski, Weidong Cai

Recently, a series of deep learning based segmentation methods have been proposed to improve the quality of raw 3D optical image stacks by removing noises and restoring neuronal structures from low-contrast background.

Representation Learning Segmentation

Discriminative Latent Semantic Graph for Video Captioning

1 code implementation8 Aug 2021 Yang Bai, Junyan Wang, Yang Long, Bingzhang Hu, Yang song, Maurice Pagnucco, Yu Guan

Video captioning aims to automatically generate natural language sentences that can describe the visual contents of a given video.

Object Sentence +2

SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations

1 code implementation ICLR 2022 Chenlin Meng, Yutong He, Yang song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, Stefano Ermon

The key challenge is balancing faithfulness to the user input (e. g., hand-drawn colored strokes) and realism of the synthesized image.

Denoising Image Generation

Deep Fiber Clustering: Anatomically Informed Unsupervised Deep Learning for Fast and Effective White Matter Parcellation

no code implementations11 Jul 2021 Yuqian Chen, Chaoyi Zhang, Yang song, Nikos Makris, Yogesh Rathi, Weidong Cai, Fan Zhang, Lauren J. O'Donnell

White matter fiber clustering (WMFC) enables parcellation of white matter tractography for applications such as disease classification and anatomical tract segmentation.

Clustering Segmentation +1

CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation

4 code implementations NeurIPS 2021 Yusuke Tashiro, Jiaming Song, Yang song, Stefano Ermon

In this paper, we propose Conditional Score-based Diffusion models for Imputation (CSDI), a novel time series imputation method that utilizes score-based diffusion models conditioned on observed data.

Audio Synthesis Image Generation +3

PhotoChat: A Human-Human Dialogue Dataset with Photo Sharing Behavior for Joint Image-Text Modeling

no code implementations ACL 2021 Xiaoxue Zang, Lijuan Liu, Maria Wang, Yang song, Hao Zhang, Jindong Chen

Based on this dataset, we propose two tasks to facilitate research on image-text modeling: a photo-sharing intent prediction task that predicts whether one intends to share a photo in the next conversation turn, and a photo retrieval task that retrieves the most relevant photo according to the dialogue context.

Image Retrieval Retrieval

Sequential Recommendation with Graph Neural Networks

1 code implementation27 Jun 2021 Jianxin Chang, Chen Gao, Yu Zheng, Yiqun Hui, Yanan Niu, Yang song, Depeng Jin, Yong Li

This helps explicitly distinguish users' core interests, by forming dense clusters in the interest graph.

Metric Learning Sequential Recommendation

BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation

1 code implementation26 Jun 2021 Xinyi Wang, Tiange Xiang, Chaoyi Zhang, Yang song, Dongnan Liu, Heng Huang, Weidong Cai

We evaluate BiX-NAS on two segmentation tasks using three different medical image datasets, and the experimental results show that our BiX-NAS searched architecture achieves the state-of-the-art performance with significantly lower computational cost.

Image Segmentation Medical Image Segmentation +3

Partial Graph Reasoning for Neural Network Regularization

no code implementations3 Jun 2021 Tiange Xiang, Chaoyi Zhang, Yang song, SiQi Liu, Hongliang Yuan, Weidong Cai

This add-on graph regularizes the network during training and can be completely skipped during inference.

Anytime Sampling for Autoregressive Models via Ordered Autoencoding

1 code implementation ICLR 2021 Yilun Xu, Yang song, Sahaj Garg, Linyuan Gong, Rui Shu, Aditya Grover, Stefano Ermon

Experimentally, we demonstrate in several image and audio generation tasks that sample quality degrades gracefully as we reduce the computational budget for sampling.

Audio Generation Computational Efficiency

Single Neuron Segmentation using Graph-based Global Reasoning with Auxiliary Skeleton Loss from 3D Optical Microscope Images

no code implementations22 Jan 2021 Heng Wang, Yang song, Chaoyi Zhang, Jianhui Yu, SiQi Liu, Hanchuan Peng, Weidong Cai

One of the critical steps in improving accurate single neuron reconstruction from three-dimensional (3D) optical microscope images is the neuronal structure segmentation.

Segmentation

Maximum Likelihood Training of Score-Based Diffusion Models

3 code implementations NeurIPS 2021 Yang song, Conor Durkan, Iain Murray, Stefano Ermon

Score-based diffusion models synthesize samples by reversing a stochastic process that diffuses data to noise, and are trained by minimizing a weighted combination of score matching losses.

Ranked #6 on Image Generation on ImageNet 32x32 (bpd metric)

Data Augmentation Image Generation

How to Train Your Energy-Based Models

2 code implementations9 Jan 2021 Yang song, Diederik P. Kingma

Energy-Based Models (EBMs), also known as non-normalized probabilistic models, specify probability density or mass functions up to an unknown normalizing constant.

Understanding Classifiers with Generative Models

no code implementations1 Jan 2021 Laëtitia Shao, Yang song, Stefano Ermon

Although deep neural networks are effective on supervised learning tasks, they have been shown to be brittle.

Two-sample testing

Fast WordPiece Tokenization

1 code implementation EMNLP 2021 Xinying Song, Alex Salcianu, Yang song, Dave Dopson, Denny Zhou

For general text, we further propose an algorithm that combines pre-tokenization (splitting the text into words) and our linear-time WordPiece method into a single pass.

Sentence

Learning Energy-Based Models by Diffusion Recovery Likelihood

2 code implementations ICLR 2021 Ruiqi Gao, Yang song, Ben Poole, Ying Nian Wu, Diederik P. Kingma

Inspired by recent progress on diffusion probabilistic models, we present a diffusion recovery likelihood method to tractably learn and sample from a sequence of EBMs trained on increasingly noisy versions of a dataset.

Image Generation

Score-Based Generative Modeling through Stochastic Differential Equations

10 code implementations ICLR 2021 Yang song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole

Combined with multiple architectural improvements, we achieve record-breaking performance for unconditional image generation on CIFAR-10 with an Inception score of 9. 89 and FID of 2. 20, a competitive likelihood of 2. 99 bits/dim, and demonstrate high fidelity generation of 1024 x 1024 images for the first time from a score-based generative model.

Colorization Density Estimation +2

Autoregressive Score Matching

no code implementations NeurIPS 2020 Chenlin Meng, Lantao Yu, Yang song, Jiaming Song, Stefano Ermon

To increase flexibility, we propose autoregressive conditional score models (AR-CSM) where we parameterize the joint distribution in terms of the derivatives of univariate log-conditionals (scores), which need not be normalized.

Density Estimation Image Denoising +1

Imitation with Neural Density Models

no code implementations NeurIPS 2021 Kuno Kim, Akshat Jindal, Yang song, Jiaming Song, Yanan Sui, Stefano Ermon

We propose a new framework for Imitation Learning (IL) via density estimation of the expert's occupancy measure followed by Maximum Occupancy Entropy Reinforcement Learning (RL) using the density as a reward.

Density Estimation Imitation Learning +2

Understanding Classifier Mistakes with Generative Models

no code implementations5 Oct 2020 Laëtitia Shao, Yang song, Stefano Ermon

From this observation, we develop a detection criteria for samples on which a classifier is likely to fail at test time.

Two-sample testing

Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network

no code implementations25 Sep 2020 Shuqing Bian, Xu Chen, Wayne Xin Zhao, Kun Zhou, Yupeng Hou, Yang song, Tao Zhang, Ji-Rong Wen

Compared with pure text-based matching models, the proposed approach is able to learn better data representations from limited or even sparse interaction data, which is more resistible to noise in training data.

Text Matching

PDAM: A Panoptic-Level Feature Alignment Framework for Unsupervised Domain Adaptive Instance Segmentation in Microscopy Images

1 code implementation11 Sep 2020 Dongnan Liu, Donghao Zhang, Yang song, Fan Zhang, Lauren O'Donnell, Heng Huang, Mei Chen, Weidong Cai

In this work, we present an unsupervised domain adaptation (UDA) method, named Panoptic Domain Adaptive Mask R-CNN (PDAM), for unsupervised instance segmentation in microscopy images.

Instance Segmentation Segmentation +3

Efficient Learning of Generative Models via Finite-Difference Score Matching

1 code implementation NeurIPS 2020 Tianyu Pang, Kun Xu, Chongxuan Li, Yang song, Stefano Ermon, Jun Zhu

Several machine learning applications involve the optimization of higher-order derivatives (e. g., gradients of gradients) during training, which can be expensive in respect to memory and computation even with automatic differentiation.

BiO-Net: Learning Recurrent Bi-directional Connections for Encoder-Decoder Architecture

1 code implementation1 Jul 2020 Tiange Xiang, Chaoyi Zhang, Dongnan Liu, Yang song, Heng Huang, Weidong Cai

U-Net has become one of the state-of-the-art deep learning-based approaches for modern computer vision tasks such as semantic segmentation, super resolution, image denoising, and inpainting.

Image Denoising Semantic Segmentation +1

Improved Techniques for Training Score-Based Generative Models

8 code implementations NeurIPS 2020 Yang Song, Stefano Ermon

Score-based generative models can produce high quality image samples comparable to GANs, without requiring adversarial optimization.

Image Generation

ICE-GAN: Identity-aware and Capsule-Enhanced GAN with Graph-based Reasoning for Micro-Expression Recognition and Synthesis

1 code implementation9 May 2020 Jianhui Yu, Chaoyi Zhang, Yang song, Weidong Cai

Micro-expressions are reflections of people's true feelings and motives, which attract an increasing number of researchers into the study of automatic facial micro-expression recognition.

Generative Adversarial Network Micro Expression Recognition +1

Diversity can be Transferred: Output Diversification for White- and Black-box Attacks

1 code implementation NeurIPS 2020 Yusuke Tashiro, Yang song, Stefano Ermon

Adversarial attacks often involve random perturbations of the inputs drawn from uniform or Gaussian distributions, e. g., to initialize optimization-based white-box attacks or generate update directions in black-box attacks.

Training Deep Energy-Based Models with f-Divergence Minimization

1 code implementation ICML 2020 Lantao Yu, Yang song, Jiaming Song, Stefano Ermon

Experimental results demonstrate the superiority of f-EBM over contrastive divergence, as well as the benefits of training EBMs using f-divergences other than KL.

Gaussianization Flows

3 code implementations4 Mar 2020 Chenlin Meng, Yang song, Jiaming Song, Stefano Ermon

Iterative Gaussianization is a fixed-point iteration procedure that can transform any continuous random vector into a Gaussian one.

Permutation Invariant Graph Generation via Score-Based Generative Modeling

1 code implementation2 Mar 2020 Chenhao Niu, Yang song, Jiaming Song, Shengjia Zhao, Aditya Grover, Stefano Ermon

In particular, we design a permutation equivariant, multi-channel graph neural network to model the gradient of the data distribution at the input graph (a. k. a., the score function).

Graph Generation

Panoptic Feature Fusion Net: A Novel Instance Segmentation Paradigm for Biomedical and Biological Images

1 code implementation15 Feb 2020 Dongnan Liu, Donghao Zhang, Yang song, Heng Huang, Weidong Cai

Specifically, our proposed PFFNet contains a residual attention feature fusion mechanism to incorporate the instance prediction with the semantic features, in order to facilitate the semantic contextual information learning in the instance branch.

Instance Segmentation Medical Image Segmentation +2

Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving

1 code implementation10 Feb 2020 Yang Song, Chenlin Meng, Renjie Liao, Stefano Ermon

Feedforward computation, such as evaluating a neural network or sampling from an autoregressive model, is ubiquitous in machine learning.

Region and Object based Panoptic Image Synthesis through Conditional GANs

no code implementations14 Dec 2019 Heng Wang, Donghao Zhang, Yang song, Heng Huang, Mei Chen, Weidong Cai

Our contribution consists of the proposal of a significant task worth investigating and a naive baseline of solving it.

Image-to-Image Translation Translation

Error-Correcting Output Codes with Ensemble Diversity for Robust Learning in Neural Networks

no code implementations30 Nov 2019 Yang Song, Qiyu Kang, Wee Peng Tay

Though deep learning has been applied successfully in many scenarios, malicious inputs with human-imperceptible perturbations can make it vulnerable in real applications.

Multi-class Classification

Domain Adaptation for Person-Job Fit with Transferable Deep Global Match Network

no code implementations IJCNLP 2019 Shuqing Bian, Wayne Xin Zhao, Yang song, Tao Zhang, Ji-Rong Wen

Furthermore, we extend the match network and implement domain adaptation in three levels, sentence-level representation, sentence-level match, and global match.

Domain Adaptation Sentence

Representation Learning with Ordered Relation Paths for Knowledge Graph Completion

1 code implementation IJCNLP 2019 Yao Zhu, Hongzhi Liu, Zhonghai Wu, Yang song, Tao Zhang

Recently, a few methods take relation paths into consideration but pay less attention to the order of relations in paths which is important for reasoning.

Ranked #3 on Link Prediction on FB15k (MR metric)

Link Prediction Relation +1

Extremely Small BERT Models from Mixed-Vocabulary Training

no code implementations EACL 2021 Sanqiang Zhao, Raghav Gupta, Yang song, Denny Zhou

Pretrained language models like BERT have achieved good results on NLP tasks, but are impractical on resource-limited devices due to memory footprint.

Knowledge Distillation Language Modelling +2

Towards Certified Defense for Unrestricted Adversarial Attacks

no code implementations25 Sep 2019 Shengjia Zhao, Yang song, Stefano Ermon

Our defense draws inspiration from differential privacy, and is based on intentionally adding noise to the classifier's outputs to limit the attacker's knowledge about the parameters.

Adversarial Attack

A General Data Renewal Model for Prediction Algorithms in Industrial Data Analytics

no code implementations22 Aug 2019 Hongzhi Wang, Yijie Yang, Yang song

In industrial data analytics, one of the fundamental problems is to utilize the temporal correlation of the industrial data to make timely predictions in the production process, such as fault prediction and yield prediction.

LSTM-based Flow Prediction

no code implementations9 Aug 2019 Hongzhi Wang, Yang song, Shihan Tang

In this paper, a method of prediction on continuous time series variables from the production or flow -- an LSTM algorithm based on multivariate tuning -- is proposed.

Time Series Time Series Analysis

MintNet: Building Invertible Neural Networks with Masked Convolutions

1 code implementation NeurIPS 2019 Yang Song, Chenlin Meng, Stefano Ermon

To demonstrate their flexibility, we show that our invertible neural networks are competitive with ResNets on MNIST and CIFAR-10 classification.

Image Generation

Generative Modeling by Estimating Gradients of the Data Distribution

11 code implementations NeurIPS 2019 Yang Song, Stefano Ermon

We introduce a new generative model where samples are produced via Langevin dynamics using gradients of the data distribution estimated with score matching.

Image Inpainting

Generating Long and Informative Reviews with Aspect-Aware Coarse-to-Fine Decoding

1 code implementation ACL 2019 Junyi Li, Wayne Xin Zhao, Ji-Rong Wen, Yang song

In this paper, we propose a novel review generation model by characterizing an elaborately designed aspect-aware coarse-to-fine generation process.

Review Generation Sentence +1

Geo-Aware Networks for Fine-Grained Recognition

1 code implementation4 Jun 2019 Grace Chu, Brian Potetz, Weijun Wang, Andrew Howard, Yang song, Fernando Brucher, Thomas Leung, Hartwig Adam

By leveraging geolocation information we improve top-1 accuracy in iNaturalist from 70. 1% to 79. 0% for a strong baseline image-only model.

Fine-Grained Image Classification General Classification

Sliced Score Matching: A Scalable Approach to Density and Score Estimation

6 code implementations17 May 2019 Yang Song, Sahaj Garg, Jiaxin Shi, Stefano Ermon

However, it has been so far limited to simple, shallow models or low-dimensional data, due to the difficulty of computing the Hessian of log-density functions.

Variational Inference

Class-Balanced Loss Based on Effective Number of Samples

8 code implementations CVPR 2019 Yin Cui, Menglin Jia, Tsung-Yi Lin, Yang song, Serge Belongie

We design a re-weighting scheme that uses the effective number of samples for each class to re-balance the loss, thereby yielding a class-balanced loss.

Image Classification Long-tail Learning

Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning

1 code implementation3 Dec 2018 Zhibo Wang, Mengkai Song, Zhifei Zhang, Yang song, Qian Wang, Hairong Qi

Although the state-of-the-art attacking techniques that incorporated the advance of Generative adversarial networks (GANs) could construct class representatives of the global data distribution among all clients, it is still challenging to distinguishably attack a specific client (i. e., user-level privacy leakage), which is a stronger privacy threat to precisely recover the private data from a specific client.

Edge-computing Federated Learning +1

Learning to Recommend with Multiple Cascading Behaviors

no code implementations21 Sep 2018 Chen Gao, Xiangnan He, Dahua Gan, Xiangning Chen, Fuli Feng, Yong Li, Tat-Seng Chua, Lina Yao, Yang song, Depeng Jin

To fully exploit the signal in the data of multiple types of behaviors, we perform a joint optimization based on the multi-task learning framework, where the optimization on a behavior is treated as a task.

Multi-Task Learning Recommendation Systems

Deep Dual Pyramid Network for Barcode Segmentation using Barcode-30k Database

no code implementations31 Jul 2018 Qijie Zhao, Feng Ni, Yang song, Yongtao Wang, Zhi Tang

Specifically, a synthesizing method was proposed to generate well-annotated images containing barcode and QR code labels, which contributes to largely decrease the annotation time.

Segmentation Semantic Segmentation

3D Global Convolutional Adversarial Network\\ for Prostate MR Volume Segmentation

no code implementations18 Jul 2018 Haozhe Jia, Yang song, Donghao Zhang, Heng Huang, Dagan Feng, Michael Fulham, Yong Xia, Weidong Cai

In this paper, we propose a 3D Global Convolutional Adversarial Network (3D GCA-Net) to address efficient prostate MR volume segmentation.

General Classification Segmentation

Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning

1 code implementation CVPR 2018 Yin Cui, Yang song, Chen Sun, Andrew Howard, Serge Belongie

We propose a measure to estimate domain similarity via Earth Mover's Distance and demonstrate that transfer learning benefits from pre-training on a source domain that is similar to the target domain by this measure.

Fine-Grained Image Classification Fine-Grained Visual Categorization +1

Constructing Unrestricted Adversarial Examples with Generative Models

1 code implementation NeurIPS 2018 Yang Song, Rui Shu, Nate Kushman, Stefano Ermon

Then, conditioned on a desired class, we search over the AC-GAN latent space to find images that are likely under the generative model and are misclassified by a target classifier.

Generative Adversarial Network

Talking Face Generation by Conditional Recurrent Adversarial Network

1 code implementation13 Apr 2018 Yang Song, Jingwen Zhu, Dawei Li, Xiaolong Wang, Hairong Qi

Given an arbitrary face image and an arbitrary speech clip, the proposed work attempts to generating the talking face video with accurate lip synchronization while maintaining smooth transition of both lip and facial movement over the entire video clip.

Constrained Lip-synchronization Video Generation

Accelerating Natural Gradient with Higher-Order Invariance

2 code implementations ICML 2018 Yang Song, Jiaming Song, Stefano Ermon

An appealing property of the natural gradient is that it is invariant to arbitrary differentiable reparameterizations of the model.

Decoupled Learning for Conditional Adversarial Networks

1 code implementation21 Jan 2018 Zhifei Zhang, Yang song, Hairong Qi

Incorporating encoding-decoding nets with adversarial nets has been widely adopted in image generation tasks.

Image Generation

PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples

1 code implementation ICLR 2018 Yang Song, Taesup Kim, Sebastian Nowozin, Stefano Ermon, Nate Kushman

Adversarial perturbations of normal images are usually imperceptible to humans, but they can seriously confuse state-of-the-art machine learning models.

Two-sample testing

Person Re-identification Using Visual Attention

no code implementations23 Jul 2017 Alireza Rahimpour, Liu Liu, Ali Taalimi, Yang song, Hairong Qi

Despite recent attempts for solving the person re-identification problem, it remains a challenging task since a person's appearance can vary significantly when large variations in view angle, human pose, and illumination are involved.

Person Re-Identification

The iNaturalist Species Classification and Detection Dataset

18 code implementations CVPR 2018 Grant Van Horn, Oisin Mac Aodha, Yang song, Yin Cui, Chen Sun, Alex Shepard, Hartwig Adam, Pietro Perona, Serge Belongie

Existing image classification datasets used in computer vision tend to have a uniform distribution of images across object categories.

General Classification Image Classification

Learning Unified Embedding for Apparel Recognition

no code implementations19 Jul 2017 Yang Song, Yuan Li, Bo Wu, Chao-Yeh Chen, Xiao Zhang, Hartwig Adam

To ease the training difficulty, a novel learning scheme is proposed by using the output from specialized models as learning targets so that L2 loss can be used instead of triplet loss.

Retrieval

r-BTN: Cross-domain Face Composite and Synthesis from Limited Facial Patches

no code implementations2 Jun 2017 Yang Song, Zhifei Zhang, Hairong Qi

A more generalized question is that if a large proportion (e. g., more than 50%) of the face/sketch is missing, can a realistic whole face sketch/image still be estimated.

Facial Inpainting Transfer Learning

Age Progression/Regression by Conditional Adversarial Autoencoder

4 code implementations CVPR 2017 Zhifei Zhang, Yang song, Hairong Qi

In CAAE, the face is first mapped to a latent vector through a convolutional encoder, and then the vector is projected to the face manifold conditional on age through a deconvolutional generator.

Attribute regression

Stochastic Gradient Geodesic MCMC Methods

no code implementations NeurIPS 2016 Chang Liu, Jun Zhu, Yang song

We propose two stochastic gradient MCMC methods for sampling from Bayesian posterior distributions defined on Riemann manifolds with a known geodesic flow, e. g. hyperspheres.

Topic Models

Speed/accuracy trade-offs for modern convolutional object detectors

14 code implementations CVPR 2017 Jonathan Huang, Vivek Rathod, Chen Sun, Menglong Zhu, Anoop Korattikara, Alireza Fathi, Ian Fischer, Zbigniew Wojna, Yang song, Sergio Guadarrama, Kevin Murphy

On the opposite end in which accuracy is critical, we present a detector that achieves state-of-the-art performance measured on the COCO detection task.

Ranked #220 on Object Detection on COCO test-dev (using extra training data)

Object object-detection +1

Derivative Delay Embedding: Online Modeling of Streaming Time Series

1 code implementation24 Sep 2016 Zhifei Zhang, Yang song, Wei Wang, Hairong Qi

The staggering amount of streaming time series coming from the real world calls for more efficient and effective online modeling solution.

General Classification Time Series +1

Kernel Bayesian Inference with Posterior Regularization

no code implementations NeurIPS 2016 Yang Song, Jun Zhu, Yong Ren

We propose a vector-valued regression problem whose solution is equivalent to the reproducing kernel Hilbert space (RKHS) embedding of the Bayesian posterior distribution.

Bayesian Inference regression

Improving the Robustness of Deep Neural Networks via Stability Training

no code implementations CVPR 2016 Stephan Zheng, Yang song, Thomas Leung, Ian Goodfellow

In this paper we address the issue of output instability of deep neural networks: small perturbations in the visual input can significantly distort the feature embeddings and output of a neural network.

General Classification

Bayesian Matrix Completion via Adaptive Relaxed Spectral Regularization

1 code implementation3 Dec 2015 Yang Song, Jun Zhu

Bayesian matrix completion has been studied based on a low-rank matrix factorization formulation with promising results.

Bayesian Inference Collaborative Filtering +1

Fusing Subcategory Probabilities for Texture Classification

no code implementations CVPR 2015 Yang Song, Weidong Cai, Qing Li, Fan Zhang, David Dagan Feng, Heng Huang

Texture, as a fundamental characteristic of objects, has attracted much attention in computer vision research.

Classification Clustering +2

A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems

1 code implementation WWW 2015 Ali Elkahky, Yang song, Xiaodong He

We extend the model to jointly learn from features of items from different domains and user features by introducing a multi-view Deep Learning model.

News Recommendation Recommendation Systems

An Overview of Microsoft Academic Service (MAS) and Applications

no code implementations WWW 2015 Arnab Sinha, Zhihong Shen, Yang song, Hao Ma, Darrin Eide, Bo-June (Paul) Hsu, Kuansan Wang

In addition to obtaining these entities from the publisher feeds as in the previous effort, we in this version include data mining results from the Web index and an in-house knowledge base from Bing, a major commercial search engine.

Learning Fine-grained Image Similarity with Deep Ranking

6 code implementations CVPR 2014 Jiang Wang, Yang song, Thomas Leung, Chuck Rosenberg, Jinbin Wang, James Philbin, Bo Chen, Ying Wu

This paper proposes a deep ranking model that employs deep learning techniques to learn similarity metric directly from images. It has higher learning capability than models based on hand-crafted features.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.