Search Results for author: Yu Yang

Found 71 papers, 23 papers with code

SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models

no code implementations12 Mar 2024 Yu Yang, Siddhartha Mishra, Jeffrey N Chiang, Baharan Mirzasoleiman

In clinical text summarization on the MIMIC-III dataset (Johnson et al., 2016), S2L again outperforms training on the full dataset using only 50% of the data.

Math Text Summarization

Heterogeneity-aware Cross-school Electives Recommendation: a Hybrid Federated Approach

no code implementations19 Feb 2024 Chengyi Ju, Jiannong Cao, Yu Yang, Zhen-Qun Yang, Ho Man Lee

In response, we propose HFRec, a heterogeneity-aware hybrid federated recommender system designed for cross-school elective course recommendations.

Recommendation Systems

Boosting Gradient Ascent for Continuous DR-submodular Maximization

no code implementations16 Jan 2024 Qixin Zhang, Zongqi Wan, Zengde Deng, Zaiyi Chen, Xiaoming Sun, Jialin Zhang, Yu Yang

The fundamental idea of our boosting technique is to exploit non-oblivious search to derive a novel auxiliary function $F$, whose stationary points are excellent approximations to the global maximum of the original DR-submodular objective $f$.

Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations

no code implementations18 Dec 2023 Zilin Wang, Haolin Zhuang, Lu Li, Yinmin Zhang, Junjie Zhong, Jun Chen, Yu Yang, Boshi Tang, Zhiyong Wu

This paper presents an Exploratory 3D Dance generation framework, E3D2, designed to address the exploration capability deficiency in existing music-conditioned 3D dance generation models.

Camera-based 3D Semantic Scene Completion with Sparse Guidance Network

1 code implementation10 Dec 2023 Jianbiao Mei, Yu Yang, Mengmeng Wang, Junyu Zhu, Xiangrui Zhao, Jongwon Ra, Laijian Li, Yong liu

Semantic scene completion (SSC) aims to predict the semantic occupancy of each voxel in the entire 3D scene from limited observations, which is an emerging and critical task for autonomous driving.

3D Semantic Scene Completion Autonomous Driving

Decoding Data Quality via Synthetic Corruptions: Embedding-guided Pruning of Code Data

no code implementations5 Dec 2023 Yu Yang, Aaditya K. Singh, Mostafa Elhoushi, Anas Mahmoud, Kushal Tirumala, Fabian Gloeckle, Baptiste Rozière, Carole-Jean Wu, Ari S. Morcos, Newsha Ardalani

Armed with this knowledge, we devise novel pruning metrics that operate in embedding space to identify and remove low-quality entries in the Stack dataset.

Code Generation

Moving Sampling Physics-informed Neural Networks induced by Moving Mesh PDE

no code implementations14 Nov 2023 Yu Yang, Qihong Yang, Yangtao Deng, Qiaolin He

In this work, we propose an end-to-end adaptive sampling neural network (MMPDE-Net) based on the moving mesh method, which can adaptively generate new sampling points by solving the moving mesh PDE.

Training A Multi-stage Deep Classifier with Feedback Signals

no code implementations12 Nov 2023 Chao Xu, Yu Yang, Rongzhao Wang, Guan Wang, Bojia Lin

Multi-Stage Classifier (MSC) - several classifiers working sequentially in an arranged order and classification decision is partially made at each step - is widely used in industrial applications for various resource limitation reasons.

Binary Classification

Bayes-enhanced Multi-view Attention Networks for Robust POI Recommendation

no code implementations1 Nov 2023 Jiangnan Xia, Yu Yang, Senzhang Wang, Hongzhi Yin, Jiannong Cao, Philip S. Yu

To this end, we investigate a novel problem of robust POI recommendation by considering the uncertainty factors of the user check-ins, and proposes a Bayes-enhanced Multi-view Attention Network.

Data Augmentation Representation Learning

Boosting Summarization with Normalizing Flows and Aggressive Training

1 code implementation1 Nov 2023 Yu Yang, Xiaotong Shen

This paper presents FlowSUM, a normalizing flows-based variational encoder-decoder framework for Transformer-based summarization.

Knowledge Distillation Text Summarization

Optimal Batched Best Arm Identification

no code implementations21 Oct 2023 Tianyuan Jin, Yu Yang, Jing Tang, Xiaokui Xiao, Pan Xu

Based on Tri-BBAI, we further propose the almost optimal batched best arm identification (Opt-BBAI) algorithm, which is the first algorithm that achieves the near-optimal sample and batch complexity in the non-asymptotic setting (i. e., $\delta>0$ is arbitrarily fixed), while enjoying the same batch and sample complexity as Tri-BBAI when $\delta$ tends to zero.

Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality

no code implementations10 Oct 2023 Xuxi Chen, Yu Yang, Zhangyang Wang, Baharan Mirzasoleiman

Dataset distillation aims to minimize the time and memory needed for training deep networks on large datasets, by creating a small set of synthetic images that has a similar generalization performance to that of the full dataset.

Sieve: Multimodal Dataset Pruning Using Image Captioning Models

1 code implementation3 Oct 2023 Anas Mahmoud, Mostafa Elhoushi, Amro Abbas, Yu Yang, Newsha Ardalani, Hugh Leather, Ari Morcos

We propose a pruning signal, Sieve, that employs synthetic captions generated by image-captioning models pretrained on small, diverse, and well-aligned image-text pairs to evaluate the alignment of noisy image-text pairs.

Image Captioning Language Modelling +1

Non-Uniform Sampling Reconstruction for Symmetrical NMR Spectroscopy by Exploiting Inherent Symmetry

no code implementations24 Sep 2023 Enping Lin, Ze Fang, Yuqing Huang, Yu Yang, Zhong Chen

Symmetrical NMR spectroscopy constitutes a vital branch of multidimensional NMR spectroscopy, providing a powerful tool for the structural elucidation of biological macromolecules.

Parallel Knowledge Enhancement based Framework for Multi-behavior Recommendation

1 code implementation9 Aug 2023 Chang Meng, Chenhao Zhai, Yu Yang, Hengyu Zhang, Xiu Li

In the fusion step, advanced neural networks are used to model the hierarchical correlations between user behaviors.

Multi-Task Learning

PANet: LiDAR Panoptic Segmentation with Sparse Instance Proposal and Aggregation

1 code implementation27 Jun 2023 Jianbiao Mei, Yu Yang, Mengmeng Wang, Xiaojun Hou, Laijian Li, Yong liu

Firstly, we propose a non-learning Sparse Instance Proposal (SIP) module with the ``sampling-shifting-grouping" scheme to directly group thing points into instances from the raw point cloud efficiently.

Autonomous Driving Instance Segmentation +2

SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV Fusion

1 code implementation27 Jun 2023 Jianbiao Mei, Yu Yang, Mengmeng Wang, Tianxin Huang, Xuemeng Yang, Yong liu

However, how to effectively exploit the relationships between the semantic context in semantic segmentation and geometric structure in scene completion remains under exploration.

Autonomous Driving Scene Understanding +1

Towards Mitigating Spurious Correlations in the Wild: A Benchmark and a more Realistic Dataset

1 code implementation21 Jun 2023 Siddharth Joshi, Yu Yang, Yihao Xue, Wenhan Yang, Baharan Mirzasoleiman

Deep neural networks often exploit non-predictive features that are spuriously correlated with class labels, leading to poor performance on groups of examples without such features.

Towards Sustainable Learning: Coresets for Data-efficient Deep Learning

1 code implementation2 Jun 2023 Yu Yang, Hao Kang, Baharan Mirzasoleiman

To improve the efficiency and sustainability of learning deep models, we propose CREST, the first scalable framework with rigorous theoretical guarantees to identify the most valuable examples for training non-convex models, particularly deep networks.

Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias

no code implementations30 May 2023 Yu Yang, Eric Gan, Gintare Karolina Dziugaite, Baharan Mirzasoleiman

In this work, we provide the first theoretical analysis of the effect of simplicity bias on learning spurious correlations.

Inductive Bias

Few-shot Adaption to Distribution Shifts By Mixing Source and Target Embeddings

no code implementations23 May 2023 Yihao Xue, Ali Payani, Yu Yang, Baharan Mirzasoleiman

Pretrained machine learning models need to be adapted to distribution shifts when deployed in new target environments.

Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning

no code implementations8 Apr 2023 Yu Yang, Besmira Nushi, Hamid Palangi, Baharan Mirzasoleiman

Spurious correlations that degrade model generalization or lead the model to be right for the wrong reasons are one of the main robustness concerns for real-world deployments.

Attribute

CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning

1 code implementation ICCV 2023 Hritik Bansal, Nishad Singhi, Yu Yang, Fan Yin, Aditya Grover, Kai-Wei Chang

Multimodal contrastive pretraining has been used to train multimodal representation models, such as CLIP, on large amounts of paired image-text data.

Backdoor Attack Contrastive Learning +1

Battery Valuation and Management for Battery Swapping Station with an Intertemporal Framework

no code implementations28 Feb 2023 Xinjiang Chen, Yu Yang, Jianxiao Wang, Jie Song, Guannan He

Battery swapping as a business model for battery energy storage (BES) has great potential in future integrated low-carbon energy and transportation systems.

Management

Machine Learning for Smart and Energy-Efficient Buildings

no code implementations27 Nov 2022 Hari Prasanna Das, Yu-Wen Lin, Utkarsha Agwan, Lucas Spangher, Alex Devonport, Yu Yang, Jan Drgona, Adrian Chong, Stefano Schiavon, Costas J. Spanos

In this work, we review the ways in which machine learning has been leveraged to make buildings smart and energy-efficient.

ILSGAN: Independent Layer Synthesis for Unsupervised Foreground-Background Segmentation

1 code implementation25 Nov 2022 Qiran Zou, Yu Yang, Wing Yin Cheung, Chang Liu, Xiangyang Ji

Unsupervised foreground-background segmentation aims at extracting salient objects from cluttered backgrounds, where Generative Adversarial Network (GAN) approaches, especially layered GANs, show great promise.

Generative Adversarial Network Image Generation +4

Learning to Annotate Part Segmentation with Gradient Matching

1 code implementation ICLR 2022 Yu Yang, Xiaotian Cheng, Hakan Bilen, Xiangyang Ji

The success of state-of-the-art deep neural networks heavily relies on the presence of large-scale labelled datasets, which are extremely expensive and time-consuming to annotate.

Segmentation

Distilling Representations from GAN Generator via Squeeze and Span

1 code implementation6 Nov 2022 Yu Yang, Xiaotian Cheng, Chang Liu, Hakan Bilen, Xiangyang Ji

In recent years, generative adversarial networks (GANs) have been an actively studied topic and shown to successfully produce high-quality realistic images in various domains.

Representation Learning

Local Manifold Augmentation for Multiview Semantic Consistency

no code implementations5 Nov 2022 Yu Yang, Wing Yin Cheung, Chang Liu, Xiangyang Ji

Multiview self-supervised representation learning roots in exploring semantic consistency across data of complex intra-class variation.

Representation Learning Self-Supervised Learning

Not All Poisons are Created Equal: Robust Training against Data Poisoning

2 code implementations18 Oct 2022 Yu Yang, Tian Yu Liu, Baharan Mirzasoleiman

Data poisoning causes misclassification of test time target examples by injecting maliciously crafted samples in the training data.

Data Poisoning

Neural Networks Based on Power Method and Inverse Power Method for Solving Linear Eigenvalue Problems

1 code implementation22 Sep 2022 Qihong Yang, Yangtao Deng, Yu Yang, Qiaolin He, Shiquan Zhang

In this article, we propose two kinds of neural networks inspired by power method and inverse power method to solve linear eigenvalue problems.

Sequence-to-Set Generative Models

1 code implementation19 Sep 2022 Longtao Tang, Ying Zhou, Yu Yang

We present GRU2Set, which is an instance of our sequence-to-set method and employs the famous GRU model as the sequence generative model.

Deep Feature Selection for Anomaly Detection Based on Pretrained Network and Gaussian Discriminative Analysis

1 code implementation IEEE Open Journal of Instrumentation and Measurement (Volume: 1) 2022 Jie Lin, Song Chen, Enping Lin, Yu Yang

Deep learning neural network serves as a powerful tool for visual anomaly detection (AD) and fault diagnosis, attributed to its strong abstractive interpretation ability in the representation domain.

Anomaly Detection feature selection

Communication-Efficient Decentralized Online Continuous DR-Submodular Maximization

no code implementations18 Aug 2022 Qixin Zhang, Zengde Deng, Xiangru Jian, Zaiyi Chen, Haoyuan Hu, Yu Yang

Maximizing a monotone submodular function is a fundamental task in machine learning, economics, and statistics.

Online Learning for Non-monotone Submodular Maximization: From Full Information to Bandit Feedback

no code implementations16 Aug 2022 Qixin Zhang, Zengde Deng, Zaiyi Chen, Kuangqi Zhou, Haoyuan Hu, Yu Yang

In this paper, we revisit the online non-monotone continuous DR-submodular maximization problem over a down-closed convex set, which finds wide real-world applications in the domain of machine learning, economics, and operations research.

Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks

1 code implementation14 Aug 2022 Tian Yu Liu, Yu Yang, Baharan Mirzasoleiman

We make the key observation that attacks introduce local sharp regions of high training loss, which when minimized, results in learning the adversarial perturbations and makes the attack successful.

Data Poisoning

Towards Better Dermoscopic Image Feature Representation Learning for Melanoma Classification

1 code implementation15 Jul 2022 Chenghui Yu, Mingkang Tang, ShengGe Yang, Mingqing Wang, Zhe Xu, Jiangpeng Yan, HanMo Chen, Yu Yang, Xiao-jun Zeng, Xiu Li

Deep learning-based melanoma classification with dermoscopic images has recently shown great potential in automatic early-stage melanoma diagnosis.

Data Augmentation Denoising +2

Time-aware Dynamic Graph Embedding for Asynchronous Structural Evolution

no code implementations1 Jul 2022 Yu Yang, Hongzhi Yin, Jiannong Cao, Tong Chen, Quoc Viet Hung Nguyen, Xiaofang Zhou, Lei Chen

Meanwhile, we treat each edge sequence as a whole and embed its ToV of the first vertex to further encode the time-sensitive information.

Dynamic graph embedding Graph Mining

MNL-Bandits under Inventory and Limited Switches Constraints

no code implementations22 Apr 2022 Hongbin Zhang, Yu Yang, Feng Wu, Qixin Zhang

Optimizing the assortment of products to display to customers is a key to increasing revenue for both offline and online retailers.

Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attention

1 code implementation CVPR 2022 Yu Yang, Seungbae Kim, Jungseock Joo

We also demonstrate a novel application of our method for unsupervised dataset bias analysis which allows us to automatically discover hidden biases in datasets or compare different subsets without using additional labels.

Feature Construction and Selection for PV Solar Power Modeling

no code implementations13 Feb 2022 Yu Yang, Jia Mao, Richard Nguyen, Annas Tohmeh, Hen-Geul Yeh

A machine learning framework for 1-hour ahead solar power prediction is developed in this paper based on the historical data.

BIG-bench Machine Learning feature selection +2

An Exact Method for the Daily Package Shipment Problem with Outsourcing

no code implementations8 Feb 2022 Zhuolin Wang, Rongping Zhu, Jian-Ya Ding, Yu Yang, Keyou You

The package shipment problem requires to optimally co-design paths for both packages and a heterogeneous fleet in a transit center network (TCN).

Which Style Makes Me Attractive? Interpretable Control Discovery and Counterfactual Explanation on StyleGAN

1 code implementation24 Jan 2022 Bo Li, Qiulin Wang, JiQuan Pei, Yu Yang, Xiangyang Ji

First, we propose a novel approach to disentangle latent subspace semantics by exploiting existing face analysis models, e. g., face parsers and face landmark detectors.

counterfactual Counterfactual Explanation +3

Stochastic Continuous Submodular Maximization: Boosting via Non-oblivious Function

no code implementations3 Jan 2022 Qixin Zhang, Zengde Deng, Zaiyi Chen, Haoyuan Hu, Yu Yang

In the online setting, for the first time we consider the adversarial delays for stochastic gradient feedback, under which we propose a boosting online gradient algorithm with the same non-oblivious function $F$.

Towards Transactive Energy: An Analysis of Information-related Practical Issues

no code implementations28 Dec 2021 Yue Chen, Yu Yang, Xiaoyuan Xu

The development of distributed energy resources, such as rooftop photovoltaic (PV) panels, batteries, and electric vehicles (EVs), has decentralized our power system operation, where transactive energy markets empower local energy exchanges.

Privacy Preserving

Value Activation for Bias Alleviation: Generalized-activated Deep Double Deterministic Policy Gradients

1 code implementation21 Dec 2021 Jiafei Lyu, Yu Yang, Jiangpeng Yan, Xiu Li

It is vital to accurately estimate the value function in Deep Reinforcement Learning (DRL) such that the agent could execute proper actions instead of suboptimal ones.

Continuous Control

Improving Cooperative Game Theory-based Data Valuation via Data Utility Learning

1 code implementation13 Jul 2021 Tianhao Wang, Yu Yang, Ruoxi Jia

The Shapley value (SV) and Least core (LC) are classic methods in cooperative game theory for cost/profit sharing problems.

Active Learning Data Valuation

Language Scaling for Universal Suggested Replies Model

no code implementations NAACL 2021 Qianlan Ying, Payal Bajaj, Budhaditya Deb, Yu Yang, Wei Wang, Bojia Lin, Milad Shokouhi, Xia Song, Yang Yang, Daxin Jiang

Faced with increased compute requirements and low resources for language expansion, we build a single universal model for improving the quality and reducing run-time costs of our production system.

Continual Learning Cross-Lingual Transfer

A Dimension-Insensitive Algorithm for Stochastic Zeroth-Order Optimization

no code implementations22 Apr 2021 Hongcheng Liu, Yu Yang

This paper concerns a convex, stochastic zeroth-order optimization (S-ZOO) problem.

Learning Foreground-Background Segmentation from Improved Layered GANs

no code implementations1 Apr 2021 Yu Yang, Hakan Bilen, Qiran Zou, Wing Yin Cheung, Xiangyang Ji

Deep learning approaches heavily rely on high-quality human supervision which is nonetheless expensive, time-consuming, and error-prone, especially for image segmentation task.

Generative Adversarial Network Image Segmentation +3

Comprehensible Counterfactual Explanation on Kolmogorov-Smirnov Test

no code implementations1 Nov 2020 Zicun Cong, Lingyang Chu, Yu Yang, Jian Pei

One challenge remained untouched is how we can obtain an explanation on why a test set fails the KS test.

Anomaly Detection Astronomy +2

Optimal Sharing and Fair Cost Allocation of Community Energy Storage

no code implementations29 Oct 2020 Yu Yang, Guoqiang Hu, Costas J. Spanos

Further, we demonstrate both the building-wise and community-wise economic benefits are enhanced with the ES sharing model over the individual ES (IES) model.

Fairness Computer Science and Game Theory

EPARS: Early Prediction of At-risk Students with Online and Offline Learning Behaviors

no code implementations6 Jun 2020 Yu Yang, Zhiyuan Wen, Jiannong Cao, Jiaxing Shen, Hongzhi Yin, Xiaofang Zhou

We propose a novel algorithm (EPARS) that could early predict STAR in a semester by modeling online and offline learning behaviors.

Management Network Embedding

A Generative Model for Sampling High-Performance and Diverse Weights for Neural Networks

no code implementations7 May 2019 Lior Deutsch, Erik Nijkamp, Yu Yang

Recent work on mode connectivity in the loss landscape of deep neural networks has demonstrated that the locus of (sub-)optimal weight vectors lies on continuous paths.

Computational Efficiency

Network Transplanting (extended abstract)

no code implementations21 Jan 2019 Quanshi Zhang, Yu Yang, Qian Yu, Ying Nian Wu

This paper focuses on a new task, i. e., transplanting a category-and-task-specific neural network to a generic, modular network without strong supervision.

Unsupervised Learning of Neural Networks to Explain Neural Networks (extended abstract)

no code implementations21 Jan 2019 Quanshi Zhang, Yu Yang, Ying Nian Wu

This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i. e., the explainer uses interpretable visual concepts to explain features in middle conv-layers of a CNN.

Knowledge Distillation Object

Explaining AlphaGo: Interpreting Contextual Effects in Neural Networks

no code implementations8 Jan 2019 Zenan Ling, Haotian Ma, Yu Yang, Robert C. Qiu, Song-Chun Zhu, Quanshi Zhang

In this paper, we propose to disentangle and interpret contextual effects that are encoded in a pre-trained deep neural network.

Unsupervised Learning of Neural Networks to Explain Neural Networks

no code implementations18 May 2018 Quanshi Zhang, Yu Yang, Yuchen Liu, Ying Nian Wu, Song-Chun Zhu

Given feature maps of a certain conv-layer of the CNN, the explainer performs like an auto-encoder, which first disentangles the feature maps into object-part features and then inverts object-part features back to features of higher conv-layers of the CNN.

Disentanglement Object

Network Transplanting

no code implementations26 Apr 2018 Quanshi Zhang, Yu Yang, Qian Yu, Ying Nian Wu

This paper focuses on a new task, i. e., transplanting a category-and-task-specific neural network to a generic, modular network without strong supervision.

Dynamic Filtering with Large Sampling Field for ConvNets

no code implementations ECCV 2018 Jialin Wu, Dai Li, Yu Yang, Chandrajit Bajaj, Xiangyang Ji

We propose a dynamic filtering strategy with large sampling field for ConvNets (LS-DFN), where the position-specific kernels learn from not only the identical position but also multiple sampled neighbor regions.

object-detection Object Detection +3

Accelerating E-Commerce Search Engine Ranking by Contextual Factor Selection

no code implementations14 Mar 2018 Zhan Yusen, Da Qing, Xiao Fei, Zeng An-xiang, Yu Yang

Solving the problem by reinforcement learning, we propose the RankCFS, which has been assessed in an off-line environment as well as a real-world on-line environment (Taobao. com).

Combinatorial Optimization Decision Making +1

Interpreting CNNs via Decision Trees

no code implementations CVPR 2019 Quanshi Zhang, Yu Yang, Haotian Ma, Ying Nian Wu

We propose to learn a decision tree, which clarifies the specific reason for each prediction made by the CNN at the semantic level.

Object

Finding Theme Communities from Database Networks

no code implementations23 Sep 2017 Lingyang Chu, Zhefeng Wang, Jian Pei, Yanyan Zhang, Yu Yang, Enhong Chen

Given a database network where each vertex is associated with a transaction database, we are interested in finding theme communities.

PIEFA: Personalized Incremental and Ensemble Face Alignment

no code implementations ICCV 2015 Xi Peng, Shaoting Zhang, Yu Yang, Dimitris N. Metaxas

Face alignment, especially on real-time or large-scale sequential images, is a challenging task with broad applications.

Face Alignment Incremental Learning

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