Search Results for author: Yang Liu

Found 802 papers, 256 papers with code

Personalized Entity Resolution with Dynamic Heterogeneous KnowledgeGraph Representations

no code implementations ACL (ECNLP) 2021 Ying Lin, Han Wang, Jiangning Chen, Tong Wang, Yue Liu, Heng Ji, Yang Liu, Premkumar Natarajan

We first build a cross-source heterogeneous knowledge graph from customer purchase history and product knowledge graph to jointly learn customer and product embeddings.

Entity Resolution

Self-Supervised Quality Estimation for Machine Translation

no code implementations EMNLP 2021 Yuanhang Zheng, Zhixing Tan, Meng Zhang, Mieradilijiang Maimaiti, Huanbo Luan, Maosong Sun, Qun Liu, Yang Liu

Quality estimation (QE) of machine translation (MT) aims to evaluate the quality of machine-translated sentences without references and is important in practical applications of MT.

Machine Translation Translation

Effective Convolutional Attention Network for Multi-label Clinical Document Classification

no code implementations EMNLP 2021 Yang Liu, Hua Cheng, Russell Klopfer, Matthew R. Gormley, Thomas Schaaf

Multi-label document classification (MLDC) problems can be challenging, especially for long documents with a large label set and a long-tail distribution over labels.

Classification Document Classification +1

Modeling Entity Knowledge for Fact Verification

no code implementations EMNLP (FEVER) 2021 Yang Liu, Chenguang Zhu, Michael Zeng

Fact verification is a challenging task of identifying the truthfulness of given claims based on the retrieval of relevant evidence texts.

Fact Verification Retrieval

Exploring Word Segmentation and Medical Concept Recognition for Chinese Medical Texts

1 code implementation NAACL (BioNLP) 2021 Yang Liu, Yuanhe Tian, Tsung-Hui Chang, Song Wu, Xiang Wan, Yan Song

Chinese word segmentation (CWS) and medical concept recognition are two fundamental tasks to process Chinese electronic medical records (EMRs) and play important roles in downstream tasks for understanding Chinese EMRs.

Chinese Word Segmentation Model Selection

Interpolation between CNNs and ResNets

no code implementations ICML 2020 Zonghan Yang, Yang Liu, Chenglong Bao, Zuoqiang Shi

Although ordinary differential equations (ODEs) provide insights for designing networks architectures, its relationship with the non-residual convolutional neural networks (CNNs) is still unclear.

Adversarial Attack Image Classification

A Hybrid System for NLPTEA-2020 CGED Shared Task

no code implementations AACL (NLP-TEA) 2020 Meiyuan Fang, Kai Fu, JiPing Wang, Yang Liu, Jin Huang, Yitao Duan

As a result, among the six tracks in the shared task, our system performs well in the correction tracks: measured in F1 score, we rank first, with the highest precision, in the TOP3 correction track and third in the TOP1 correction track, also with the highest precision.

基于词信息嵌入的汉语构词结构识别研究(Chinese Word-Formation Prediction based on Representations of Word-Related Features)

no code implementations CCL 2021 Hua Zheng, Yaqi Yan, Yue Wang, Damai Dai, Yang Liu

“作为一种意合型语言, 汉语中的构词结构刻画了构词成分之间的组合关系, 是认知、理解词义的关键。在中文信息处理领域, 此前的构词结构识别工作大多沿用句法层面的粗粒度标签, 且主要基于上下文等词间信息建模, 忽略了语素义、词义等词内信息对构词结构识别的作用。本文采用语言学视域下的构词结构标签体系, 构建汉语构词结构及相关信息数据集, 提出了一种基于Bi-LSTM和Self-attention的模型, 以此来探究词内、词间等多方面信息对构词结构识别的潜在影响和能达到的性能。实验取得了良好的预测效果, 准确率77. 87%, F1值78. 36%;同时, 对比测试揭示, 词内的语素义信息对构词结构识别具有显著的贡献, 而词间的上下文信息贡献较弱且带有较强的不稳定性。该预测方法与数据集, 将为中文信息处理的多种任务, 如语素和词结构分析、词义识别与生成、语言文字研究与词典编纂等提供新的观点和方案。”

Rethinking Data Augmentation in Text-to-text Paradigm

no code implementations COLING 2022 Yanan Chen, Yang Liu

As manually labelling data can be costly, some recent studies tend to augment the training data for improving the generalization power of machine learning models, known as data augmentation (DA).

Data Augmentation

Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs

no code implementations NAACL 2022 Sha Li, Mahdi Namazifar, Di Jin, Mohit Bansal, Heng Ji, Yang Liu, Dilek Hakkani-Tur

In this work, we propose to automatically convert the background knowledge documents into document semantic graphs and then perform knowledge selection over such graphs.

Multi-Task Learning Response Generation

中美学者学术英语写作中词汇难度特征比较研究——以计算语言学领域论文为例(A Comparative Study of the Features of Lexical Sophistication in Academic English Writing by Chinese and American)

no code implementations CCL 2021 Yonghui Xie, Yang Liu, Erhong Yang, Liner Yang

“学术英语写作在国际学术交流中的作用日益凸显, 然而对于英语非母语者, 学术英语写作是困难的, 为此本文对计算语言领域中美学者学术英语写作中词汇难度特征做比较研究。自构建1132篇中美论文全文语料库, 统计语料中484个词汇难度特征值。经过特征筛选与因子分析的降维处理得到表现较好的五个维度。最后计算中美学者论文的维度分从而比较差异, 发现美国学者的论文相较中国学者的论文中词汇单位更具常用性、二元词串更具稳固性、三元词串更具稳固性、虚词更具复杂性、词类更具关联性。主要原因在于统计特征值时借助的外部资源库与美国学者的论文更贴近, 且中国学者没有完全掌握该领域学术写作的习惯。因此, 中国学者可充分利用英语本族语者构建的资源库, 从而产出更为地道与流利的学术英语论文。”

DialogSum Challenge: Summarizing Real-Life Scenario Dialogues

no code implementations INLG (ACL) 2021 Yulong Chen, Yang Liu, Yue Zhang

We propose a shared task on summarizing real-life scenario dialogues, DialogSum Challenge, to encourage researchers to address challenges in dialogue summarization, which has been less studied by the summarization community.

Common Sense Reasoning Representation Learning

Leveraging Seq2seq Language Generation for Multi-level Product Issue Identification

no code implementations ECNLP (ACL) 2022 Yang Liu, Varnith Chordia, Hua Li, Siavash Fazeli Dehkordy, Yifei Sun, Vincent Gao, Na Zhang

To harness such information to better serve customers, in this paper, we created a machine learning approach to automatically identify product issues and uncover root causes from the customer feedback text.

Multi-Label Classification Text Generation +1

Amplifying Key Cues for Human-Object-Interaction Detection

no code implementations ECCV 2020 Yang Liu, Qingchao Chen, Andrew Zisserman

In this paper we introduce two methods to amplify key cues in the image, and also a method to combine these and other cues when considering the interaction between a human and an object.

Human-Object Interaction Detection

GPTEval: NLG Evaluation using GPT-4 with Better Human Alignment

no code implementations29 Mar 2023 Yang Liu, Dan Iter, Yichong Xu, Shuohang Wang, Ruochen Xu, Chenguang Zhu

In this work, we present GPTEval, a framework of using large language models with chain-of-thoughts (CoT) and a form-filling paradigm, to assess the quality of NLG outputs.

Dialogue Generation Text Summarization

Federated Learning without Full Labels: A Survey

no code implementations25 Mar 2023 Yilun Jin, Yang Liu, Kai Chen, Qiang Yang

Therefore, the problem of federated learning without full labels is important in real-world FL applications.

Federated Learning Self-Supervised Learning +1

Fairness Improves Learning from Noisily Labeled Long-Tailed Data

no code implementations22 Mar 2023 Jiaheng Wei, Zhaowei Zhu, Gang Niu, Tongliang Liu, Sijia Liu, Masashi Sugiyama, Yang Liu

Both long-tailed and noisily labeled data frequently appear in real-world applications and impose significant challenges for learning.


Urban Regional Function Guided Traffic Flow Prediction

no code implementations17 Mar 2023 Kuo Wang, Lingbo Liu, Yang Liu, Guanbin Li, Fan Zhou, Liang Lin

The prediction of traffic flow is a challenging yet crucial problem in spatial-temporal analysis, which has recently gained increasing interest.

Visual-Linguistic Causal Intervention for Radiology Report Generation

1 code implementation16 Mar 2023 Weixing Chen, Yang Liu, Ce Wang, Guanbin Li, Jiarui Zhu, Liang Lin

Automatic radiology report generation is essential for computer-aided diagnosis and medication guidance.

object-detection Object Detection

A Data Augmentation Method and the Embedding Mechanism for Detection and Classification of Pulmonary Nodules on Small Samples

no code implementations2 Mar 2023 Yang Liu, Yue-Jie Hou, Chen-Xin Qin, Xin-Hui Li, Si-Jing Li, Bin Wang, Chi-Chun Zhou

Result: The result of the 3DVNET model with the augmentation method for pulmonary nodule detection shows that the proposed data augmentation method outperforms the method based on generative adversarial network (GAN) framework, training accuracy improved by 1. 5%, and with embedding mechanism for pulmonary nodules classification shows that the embedding mechanism improves the accuracy and robustness for the classification of pulmonary nodules obviously, the model training accuracy is close to 1 and the model testing F1-score is 0. 90. Conclusion:he proposed data augmentation method and embedding mechanism are beneficial to improve the accuracy and robustness of the model, and can be further applied in other common diagnostic imaging tasks.

Data Augmentation Pulmonary Nodules Classification

Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training

no code implementations28 Feb 2023 Dezhao Luo, Jiabo Huang, Shaogang Gong, Hailin Jin, Yang Liu

The correlation between the vision and text is essential for video moment retrieval (VMR), however, existing methods heavily rely on separate pre-training feature extractors for visual and textual understanding.

Moment Retrieval Retrieval

Factual Consistency Oriented Speech Recognition

no code implementations24 Feb 2023 Naoyuki Kanda, Takuya Yoshioka, Yang Liu

This paper presents a novel optimization framework for automatic speech recognition (ASR) with the aim of reducing hallucinations produced by an ASR model.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

How Does In-Context Learning Help Prompt Tuning?

no code implementations22 Feb 2023 Simeng Sun, Yang Liu, Dan Iter, Chenguang Zhu, Mohit Iyyer

This motivates the use of parameter-efficient adaptation methods such as prompt tuning (PT), which adds a small number of tunable embeddings to an otherwise frozen model, and in-context learning (ICL), in which demonstrations of the task are provided to the model in natural language without any additional training.

Text Generation

FedSDG-FS: Efficient and Secure Feature Selection for Vertical Federated Learning

no code implementations21 Feb 2023 Anran Li, Hongyi Peng, Lan Zhang, Jiahui Huang, Qing Guo, Han Yu, Yang Liu

Vertical Federated Learning (VFL) enables multiple data owners, each holding a different subset of features about largely overlapping sets of data sample(s), to jointly train a useful global model.

Feature Importance Federated Learning

Semi-Analytical Electromagnetic Transient Simulation Using Differential Transformation

no code implementations18 Feb 2023 Min Xiong, Rui Yao, Yang Liu, Kai Sun, Feng Qiu

For electromagnetic transient (EMT) simulation of a power system, a state-space-based approach needs to solve state-space EMT equations by using numerical integration methods, e. g., the Euler method, Runge-Kutta methods, and trapezoidal-rule method, at small time steps.

Numerical Integration

Multimodal Federated Learning via Contrastive Representation Ensemble

1 code implementation17 Feb 2023 Qiying Yu, Yang Liu, Yimu Wang, Ke Xu, Jingjing Liu

In this work, we propose Contrastive Representation Ensemble and Aggregation for Multimodal FL (CreamFL), a multimodal federated learning framework that enables training larger server models from clients with heterogeneous model architectures and data modalities, while only communicating knowledge on public dataset.

Federated Learning Question Answering +4

KILM: Knowledge Injection into Encoder-Decoder Language Models

1 code implementation17 Feb 2023 Yan Xu, Mahdi Namazifar, Devamanyu Hazarika, Aishwarya Padmakumar, Yang Liu, Dilek Hakkani-Tür

Large pre-trained language models (PLMs) have been shown to retain implicit knowledge within their parameters.

Entity Disambiguation

Adversarial Contrastive Distillation with Adaptive Denoising

no code implementations17 Feb 2023 Yuzheng Wang, Zhaoyu Chen, Dingkang Yang, Yang Liu, Siao Liu, Wenqiang Zhang, Lizhe Qi

To this end, we propose a novel structured ARD method called Contrastive Relationship DeNoise Distillation (CRDND).

Adversarial Robustness Denoising +1

Numerical analysis of a multistable capsule system under the delayed feedback control with a constant delay

no code implementations13 Feb 2023 Zhi Zhang, Joseph Páez Chávez, Jan Sieber, Yang Liu

In this paper, we study the control of coexisting attractors in this system by using a delayed feedback controller (DFC) with a constant delay.

Event Detection

A Survey on Spectral Graph Neural Networks

no code implementations11 Feb 2023 Deyu Bo, Xiao Wang, Yang Liu, Yuan Fang, Yawen Li, Chuan Shi

Graph neural networks (GNNs) have attracted considerable attention from the research community.

Graph Representation Learning

Debiasing Recommendation by Learning Identifiable Latent Confounders

no code implementations10 Feb 2023 Qing Zhang, Xiaoying Zhang, Yang Liu, Hongning Wang, Min Gao, Jiheng Zhang, Ruocheng Guo

Confounding bias arises due to the presence of unmeasured variables (e. g., the socio-economic status of a user) that can affect both a user's exposure and feedback.

Causal Inference Recommendation Systems

Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models

1 code implementation10 Feb 2023 Yang Liu, Dingkang Yang, Yan Wang, Jing Liu, Liang Song

Video Anomaly Event Detection (VAED) is the core technology of intelligent surveillance systems aiming to temporally or spatially locate anomalous events in videos.

Anomaly Detection Event Detection +1

Mining Effective Features Using Quantum Entropy for Humor Recognition

1 code implementation7 Feb 2023 Yang Liu, Yuexian Hou

Humor recognition has been extensively studied with different methods in the past years.

PLACES: Prompting Language Models for Social Conversation Synthesis

1 code implementation7 Feb 2023 Maximillian Chen, Alexandros Papangelis, Chenyang Tao, Seokhwan Kim, Andy Rosenbaum, Yang Liu, Zhou Yu, Dilek Hakkani-Tur

Collecting high quality conversational data can be very expensive for most applications and infeasible for others due to privacy, ethical, or similar concerns.

Conversational Response Generation

Using In-Context Learning to Improve Dialogue Safety

no code implementations2 Feb 2023 Nicholas Meade, Spandana Gella, Devamanyu Hazarika, Prakhar Gupta, Di Jin, Siva Reddy, Yang Liu, Dilek Hakkani-Tür

Concretely, to generate a response to an unsafe dialogue context, we retrieve demonstrations of safe model responses to similar dialogue contexts.

Re-Ranking Retrieval

End-to-End Full-Atom Antibody Design

no code implementations1 Feb 2023 Xiangzhe Kong, Wenbing Huang, Yang Liu

Finally, the updated antibody is docked to the epitope via the alignment of the shadow paratope.

Improving Open-Domain Dialogue Evaluation with a Causal Inference Model

no code implementations31 Jan 2023 Cat P. Le, Luke Dai, Michael Johnston, Yang Liu, Marilyn Walker, Reza Ghanadan

We project these features to the dialogue level and train a dialogue-level MLP regression model, a dialogue-level LSTM, and a novel causal inference model called counterfactual-LSTM (CF-LSTM) to predict ratings.

Causal Inference Dialogue Evaluation

AudioEar: Single-View Ear Reconstruction for Personalized Spatial Audio

1 code implementation30 Jan 2023 Xiaoyang Huang, Yanjun Wang, Yang Liu, Bingbing Ni, Wenjun Zhang, Jinxian Liu, Teng Li

To this end, we propose to achieve personalized spatial audio by reconstructing 3D human ears with single-view images.

Depth Estimation

Restricted Orthogonal Gradient Projection for Continual Learning

no code implementations28 Jan 2023 Zeyuan Yang, Zonghan Yang, Peng Li, Yang Liu

The basic idea is to adopt a restricted orthogonal constraint allowing parameters optimized in the direction oblique to the whole frozen space to facilitate forward knowledge transfer while consolidating previous knowledge.

Continual Learning Transfer Learning

Tier Balancing: Towards Dynamic Fairness over Underlying Causal Factors

1 code implementation21 Jan 2023 Zeyu Tang, Yatong Chen, Yang Liu, Kun Zhang

The pursuit of long-term fairness involves the interplay between decision-making and the underlying data generating process.

Decision Making Fairness

Fixed-time synchronization for quaternion-valued memristor-based neural networks with mixed delays

no code implementations2 Jan 2023 Yanlin Zhang, Liqiao Yang, Kit Ian Kou, Yang Liu

In this paper, the fixed-time synchronization (FXTSYN) of unilateral coefficients quaternion-valued memristor-based neural networks (UCQVMNNs) with mixed delays is investigated.

Mutual Information Regularization for Vertical Federated Learning

no code implementations1 Jan 2023 Tianyuan Zou, Yang Liu, Ya-Qin Zhang

However, previous works show that parties without labels (passive parties) in VFL can infer the sensitive label information owned by the party with labels (active party) or execute backdoor attacks to VFL.

Federated Learning

EVM-CNN: Real-Time Contactless Heart Rate Estimation from Facial Video

no code implementations25 Dec 2022 Ying Qiu, Yang Liu, Juan Arteaga-Falconi, Haiwei Dong, Abdulmotaleb El Saddik

Recently, it was shown that HR information can be extracted from facial videos by spatial decomposition and temporal filtering.

Heart rate estimation

Attend to the Right Context: A Plug-and-Play Module for Content-Controllable Summarization

1 code implementation21 Dec 2022 Wen Xiao, Lesly Miculicich, Yang Liu, Pengcheng He, Giuseppe Carenini

Content-Controllable Summarization generates summaries focused on the given controlling signals.

Diff-Glat: Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning

no code implementations20 Dec 2022 Lihua Qian, Mingxuan Wang, Yang Liu, Hao Zhou

Autoregressive models can achieve high generation quality, but the sequential decoding scheme causes slow decoding speed.

Knowledge Distillation

Is Self-Attention Powerful to Learn Code Syntax and Semantics?

no code implementations20 Dec 2022 Wei Ma, Mengjie Zhao, Xiaofei Xie, Qiang Hu, Shangqing Liu, Jie Zhang, Wenhan Wang, Yang Liu

We focus on a well-known representative code model, CodeBERT, and study how it can learn code syntax and semantics by the self-attention mechanism and Masked Language Modelling (MLM) at the token level.

Code Completion Code Search +2

DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines

no code implementations20 Dec 2022 Prakhar Gupta, Yang Liu, Di Jin, Behnam Hedayatnia, Spandana Gella, Sijia Liu, Patrick Lange, Julia Hirschberg, Dilek Hakkani-Tur

These guidelines provide information about the context they are applicable to and what should be included in the response, allowing the models to generate responses that are more closely aligned with the developer's expectations and intent.

Response Generation

Prompt Gating: A Parameter Efficient Tuning Method for Zero-Shot Multi-Source Translation

no code implementations19 Dec 2022 Xuancheng Huang, Zijun Liu, Peng Li, Maosong Sun, Yang Liu

Multi-source translation (MST), which typically receives multiple source sentences of the same meaning in different languages, has been shown superior to single-source translation.


Continually Learning from Existing Models: Knowledge Accumulation for Neural Machine Translation

no code implementations18 Dec 2022 Yuanchi Zhang, Peng Li, Maosong Sun, Yang Liu

Although continually extending an existing NMT model to new domains or languages has attracted intensive interest in recent years, the equally valuable problem of continually improving a given NMT model in its domain by leveraging knowledge from an unlimited number of existing NMT models is not explored yet.

Machine Translation NMT +1

Quaternion Tensor Completion with Sparseness for Color Video Recovery

no code implementations16 Dec 2022 Liqiao Yang, Kit Ian Kou, Jifei Miao, Yang Liu, Maggie Pui Man Hoi

A novel low-rank completion algorithm based on the quaternion tensor is proposed in this paper.

Weld Defect Segmentation in Xray Image with Boundary Label Smoothing

1 code implementation sci 2022 Junhua Zhang, Minghao Guo, Pengzhi Chu, Yang Liu, Jun Chen, Huanxi Liu

Weld defect segmentation (WDS) is widely used to detect defects from X-ray images for welds, which is of practical importance for manufacturing in all industries.

Uncertain Facial Expression Recognition via Multi-task Assisted Correction

no code implementations14 Dec 2022 Yang Liu, Xingming Zhang, Janne Kauttonen, Guoying Zhao

Specifically, a confidence estimation block and a weighted regularization module are applied to highlight solid samples and suppress uncertain samples in every batch.

Action Unit Detection Facial Expression Recognition (FER)

Human Mobility Modeling During the COVID-19 Pandemic via Deep Graph Diffusion Infomax

no code implementations12 Dec 2022 Yang Liu, Yu Rong, Zhuoning Guo, Nuo Chen, Tingyang Xu, Fugee Tsung, Jia Li

To address these challenges, we formulate the micro perspective mobility modeling into computing the relevance score between a diffusion and a location, conditional on a geometric graph.

Integrating multi-type aberrations from DNA and RNA through dynamic mapping gene space for subtype-specific breast cancer driver discovery

no code implementations9 Dec 2022 Jianing Xi, Zhen Deng, Yang Liu, Qian Wang, Wen Shi

Notably, cancer driver events would occur due to not only DNA aberrations but also RNA alternations, but integrating multi-type aberrations from both DNA and RNA is still a challenging task for breast cancer drivers.


Three High-rate Beamforming Methods for Active IRS-aided Wireless Network

no code implementations5 Dec 2022 Feng Shu, Jing Liu, Yeqing Lin, Yang Liu, Zhilin Chen, Xuehui Wang, Rongen Dong, Jiangzhou Wang

To fully exploit the amplifying gain achieved by active IRS, two high-rate methods, maximum ratio reflecting (MRR) and selective ratio reflecting (SRR) are presented, which are motivated by maximum ratio combining and selective ratio combining.

Unifying Vision, Text, and Layout for Universal Document Processing

2 code implementations5 Dec 2022 Zineng Tang, ZiYi Yang, Guoxin Wang, Yuwei Fang, Yang Liu, Chenguang Zhu, Michael Zeng, Cha Zhang, Mohit Bansal

UDOP leverages the spatial correlation between textual content and document image to model image, text, and layout modalities with one uniform representation.

Document AI Image Reconstruction

Joint Secure Transmit Beamforming Designs for Integrated Sensing and Communication Systems

no code implementations1 Dec 2022 Jinjin Chu, Rang Liu, Ming Li, Yang Liu, Qian Liu

Integrated sensing and communication (ISAC), which allows individual radar and communication systems to share the same spectrum bands, is an emerging and promising technique for alleviating spectrum congestion problems.

Vertical Federated Learning

no code implementations23 Nov 2022 Yang Liu, Yan Kang, Tianyuan Zou, Yanhong Pu, Yuanqin He, Xiaozhou Ye, Ye Ouyang, Ya-Qin Zhang, Qiang Yang

Vertical Federated Learning (VFL) is a federated learning setting where multiple parties with different features about the same set of users jointly train machine learning models without exposing their raw data or model parameters.

Federated Learning Privacy Preserving

GitFL: Adaptive Asynchronous Federated Learning using Version Control

no code implementations22 Nov 2022 Ming Hu, Zeke Xia, Zhihao Yue, Jun Xia, Yihao Huang, Yang Liu, Mingsong Chen

Unlike traditional FL, the cloud server of GitFL maintains a master model (i. e., the global model) together with a set of branch models indicating the trained local models committed by selected devices, where the master model is updated based on both all the pushed branch models and their version information, and only the branch models after the pull operation are dispatched to devices.

Federated Learning Reinforcement Learning (RL)

Unsupervised Explanation Generation via Correct Instantiations

no code implementations21 Nov 2022 Sijie Cheng, Zhiyong Wu, Jiangjie Chen, Zhixing Li, Yang Liu, Lingpeng Kong

The major difficulty is finding the conflict point, where the statement contradicts our real world.

Explanation Generation

Background-Mixed Augmentation for Weakly Supervised Change Detection

1 code implementation21 Nov 2022 Rui Huang, Ruofei Wang, Qing Guo, Jieda Wei, Yuxiang Zhang, Wei Fan, Yang Liu

Change detection (CD) is to decouple object changes (i. e., object missing or appearing) from background changes (i. e., environment variations) like light and season variations in two images captured in the same scene over a long time span, presenting critical applications in disaster management, urban development, etc.

Change Detection Data Augmentation +1

UniSumm: Unified Few-shot Summarization with Multi-Task Pre-Training and Prefix-Tuning

1 code implementation17 Nov 2022 Yulong Chen, Yang Liu, Ruochen Xu, ZiYi Yang, Chenguang Zhu, Michael Zeng, Yue Zhang

The diverse demands of different summarization tasks and their high annotation costs are driving a need for few-shot summarization.

LGN-Net: Local-Global Normality Network for Video Anomaly Detection

1 code implementation14 Nov 2022 Mengyang Zhao, Xinhua Zeng, Yang Liu, Jing Liu, Di Li, Xing Hu, Chengxin Pang

Existing unsupervised VAD methods tend to learn normality from training sets consisting of only normal videos and regard instances deviating from such normality as anomalies.

Anomaly Detection Video Anomaly Detection

MAPPING: Model Average with Post-processing for Stroke Lesion Segmentation

1 code implementation11 Nov 2022 Jiayu Huo, Liyun Chen, Yang Liu, Maxence Boels, Alejandro Granados, Sebastien Ourselin, Rachel Sparks

Accurate stroke lesion segmentation plays a pivotal role in stroke rehabilitation research, to provide lesion shape and size information which can be used for quantification of the extent of the stroke and to assess treatment efficacy.

Lesion Segmentation

MACSum: Controllable Summarization with Mixed Attributes

1 code implementation9 Nov 2022 Yusen Zhang, Yang Liu, ZiYi Yang, Yuwei Fang, Yulong Chen, Dragomir Radev, Chenguang Zhu, Michael Zeng, Rui Zhang

We propose two simple and effective parameter-efficient approaches for the new task of mixed controllable summarization based on hard prompt tuning and soft prefix tuning.


Soft Augmentation for Image Classification

no code implementations9 Nov 2022 Yang Liu, Shen Yan, Laura Leal-Taixé, James Hays, Deva Ramanan

We draw inspiration from human visual classification studies and propose generalizing augmentation with invariant transforms to soft augmentation where the learning target softens non-linearly as a function of the degree of the transform applied to the sample: e. g., more aggressive image crop augmentations produce less confident learning targets.

Classification Data Augmentation +1

Egocentric Audio-Visual Noise Suppression

no code implementations7 Nov 2022 Roshan Sharma, Weipeng He, Ju Lin, Egor Lakomkin, Yang Liu, Kaustubh Kalgaonkar

In this paper, we first demonstrate that egocentric visual information is helpful for noise suppression.

Action Classification Event Detection +3

Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models

1 code implementation4 Nov 2022 Chengcheng Ma, Yang Liu, Jiankang Deng, Lingxi Xie, WeiMing Dong, Changsheng Xu

Pretrained vision-language models (VLMs) such as CLIP have shown impressive generalization capability in downstream vision tasks with appropriate text prompts.

object-detection Open Vocabulary Object Detection +1

Learning to Learn Domain-invariant Parameters for Domain Generalization

no code implementations4 Nov 2022 Feng Hou, Yao Zhang, Yang Liu, Jin Yuan, Cheng Zhong, Yang Zhang, Zhongchao shi, Jianping Fan, Zhiqiang He

Due to domain shift, deep neural networks (DNNs) usually fail to generalize well on unknown test data in practice.

Domain Generalization

SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency

1 code implementation3 Nov 2022 Yang Liu, Yao Zhang, Yixin Wang, Yang Zhang, Jiang Tian, Zhongchao shi, Jianping Fan, Zhiqiang He

To bridge the gap between the reference points of salient queries and Transformer detectors, we propose SAlient Point-based DETR (SAP-DETR) by treating object detection as a transformation from salient points to instance objects.

object-detection Object Detection

Exploiting Spatial-temporal Correlations for Video Anomaly Detection

no code implementations2 Nov 2022 Mengyang Zhao, Yang Liu, Jing Li, Xinhua Zeng

Video anomaly detection (VAD) remains a challenging task in the pattern recognition community due to the ambiguity and diversity of abnormal events.

Anomaly Detection Video Anomaly Detection

SCA: Streaming Cross-attention Alignment for Echo Cancellation

no code implementations1 Nov 2022 Yang Liu, Yangyang Shi, Yun Li, Kaustubh Kalgaonkar, Sriram Srinivasan, Xin Lei

End-to-End deep learning has shown promising results for speech enhancement tasks, such as noise suppression, dereverberation, and speech separation.

Speech Enhancement Speech Separation

Physics-aware Graph Neural Network for Accurate RNA 3D Structure Prediction

no code implementations28 Oct 2022 Shuo Zhang, Yang Liu, Lei Xie

Biological functions of RNAs are determined by their three-dimensional (3D) structures.

Drug Discovery

Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning

1 code implementation26 Oct 2022 Yifan Chen, Devamanyu Hazarika, Mahdi Namazifar, Yang Liu, Di Jin, Dilek Hakkani-Tur

Prefix-tuning, or more generally continuous prompt tuning, has become an essential paradigm of parameter-efficient transfer learning.

Language Modelling Natural Language Understanding +1

Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding

no code implementations25 Oct 2022 Maximillian Chen, Alexandros Papangelis, Chenyang Tao, Andy Rosenbaum, Seokhwan Kim, Yang Liu, Zhou Yu, Dilek Hakkani-Tur

Dialogue understanding tasks often necessitate abundant annotated data to achieve good performance and that presents challenges in low-resource settings.

Data Augmentation Dialogue Understanding +2

SeismicNet: Physics-informed neural networks for seismic wave modeling in semi-infinite domain

no code implementations25 Oct 2022 Pu Ren, Chengping Rao, Su Chen, Jian-Xun Wang, Hao Sun, Yang Liu

In this paper, we present a novel physics-informed neural network (PINN) model for seismic wave modeling in semi-infinite domain without the nedd of labeled data.

Context-Situated Pun Generation

1 code implementation24 Oct 2022 Jiao Sun, Anjali Narayan-Chen, Shereen Oraby, Shuyang Gao, Tagyoung Chung, Jing Huang, Yang Liu, Nanyun Peng

In this work, we propose a new task, context-situated pun generation, where a specific context represented by a set of keywords is provided, and the task is to first identify suitable pun words that are appropriate for the context, then generate puns based on the context keywords and the identified pun words.


ExPUNations: Augmenting Puns with Keywords and Explanations

1 code implementation24 Oct 2022 Jiao Sun, Anjali Narayan-Chen, Shereen Oraby, Alessandra Cervone, Tagyoung Chung, Jing Huang, Yang Liu, Nanyun Peng

The tasks of humor understanding and generation are challenging and subjective even for humans, requiring commonsense and real-world knowledge to master.

Explanation Generation Natural Language Understanding

Improving Radiology Summarization with Radiograph and Anatomy Prompts

no code implementations15 Oct 2022 Jinpeng Hu, Zhihong Chen, Yang Liu, Xiang Wan, Tsung-Hui Chang

The impression is crucial for the referring physicians to grasp key information since it is concluded from the findings and reasoning of radiologists.

Anatomy Contrastive Learning

FedCross: Towards Accurate Federated Learning via Multi-Model Cross Aggregation

no code implementations15 Oct 2022 Ming Hu, Peiheng Zhou, Zhihao Yue, Zhiwei Ling, Yihao Huang, Yang Liu, Mingsong Chen

Due to the remarkable performance in preserving data privacy for decentralized data scenarios, Federated Learning (FL) has been considered as a promising distributed machine learning paradigm to deal with data silos problems.

Federated Learning

Towards a Unified Multi-Dimensional Evaluator for Text Generation

1 code implementation13 Oct 2022 Ming Zhong, Yang Liu, Da Yin, Yuning Mao, Yizhu Jiao, PengFei Liu, Chenguang Zhu, Heng Ji, Jiawei Han

We re-frame NLG evaluation as a Boolean Question Answering (QA) task, and by guiding the model with different questions, we can use one evaluator to evaluate from multiple dimensions.

Question Answering Response Generation +3

Task Compass: Scaling Multi-task Pre-training with Task Prefix

1 code implementation12 Oct 2022 Zhuosheng Zhang, Shuohang Wang, Yichong Xu, Yuwei Fang, Wenhao Yu, Yang Liu, Hai Zhao, Chenguang Zhu, Michael Zeng

Leveraging task-aware annotated data as supervised signals to assist with self-supervised learning on large-scale unlabeled data has become a new trend in pre-training language models.

Data Augmentation Multi-Task Learning +1

Exploring Interactions and Regulations in Collaborative Learning: An Interdisciplinary Multimodal Dataset

no code implementations11 Oct 2022 Yante Li, Yang Liu, KhÁnh Nguyen, Henglin Shi, Eija Vuorenmaa, Sanna Jarvela, Guoying Zhao

Collaborative learning is an educational approach that enhances learning through shared goals and working together.

Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributes

1 code implementation6 Oct 2022 Zhaowei Zhu, Yuanshun Yao, Jiankai Sun, Hang Li, Yang Liu

Our theoretical analyses show that directly using proxy models can give a false sense of (un)fairness.


Joint Beamforming Designs for Active Reconfigurable Intelligent Surface: A Sub-Connected Array Architecture

no code implementations5 Oct 2022 Qi Zhu, Ming Li, Rang Liu, Yang Liu, Qian Liu

Affected by the "double fading" effect, however, conventional passive RIS cannot bring considerable performance improvement when users are not close enough to RIS.

Revealing Unobservables by Deep Learning: Generative Element Extraction Networks (GEEN)

no code implementations4 Oct 2022 Yingyao Hu, Yang Liu, Jiaxiong Yao

Latent variable models are crucial in scientific research, where a key variable, such as effort, ability, and belief, is unobserved in the sample but needs to be identified.

Large-Scale Spatial Cross-Calibration of Hinode/SOT-SP and SDO/HMI

no code implementations29 Sep 2022 David F. Fouhey, Richard E. L. Higgins, Spiro K. Antiochos, Graham Barnes, Marc L. DeRosa, J. Todd Hoeksema, K. D. Leka, Yang Liu, Peter W. Schuck, Tamas I. Gombosi

Second, analysis of over 12, 000 scans show that the pointing information is often incorrect by dozens of arcseconds with a strong bias.

Resource Allocation and Resolution Control in the Metaverse with Mobile Augmented Reality

no code implementations28 Sep 2022 Peiyuan Si, Jun Zhao, Huimei Han, Kwok-Yan Lam, Yang Liu

With the development of blockchain and communication techniques, the Metaverse is considered as a promising next-generation Internet paradigm, which enables the connection between reality and the virtual world.

Implicit Conversion of Manifold B-Rep Solids by Neural Halfspace Representation

1 code implementation21 Sep 2022 Hao-Xiang Guo, Yang Liu, Hao Pan, Baining Guo

We present a novel implicit representation -- neural halfspace representation (NH-Rep), to convert manifold B-Rep solids to implicit representations.

Surface Reconstruction

Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training

1 code implementation15 Sep 2022 Zhihong Chen, Yuhao Du, Jinpeng Hu, Yang Liu, Guanbin Li, Xiang Wan, Tsung-Hui Chang

Besides, we conduct further analysis to better verify the effectiveness of different components of our approach and various settings of pre-training.

Self-Supervised Learning

Optimization for Reflection and Transmission Dual-Functional Active RIS-Assisted Systems

no code implementations5 Sep 2022 Yanan Ma, Ming Li, Yang Liu, Qingqing Wu, Qian Liu

Reconfigurable intelligent surface (RIS) has been deemed as one of potential components of future wireless communication systems because it can adaptively manipulate the wireless propagation environment with low-cost passive devices.

Learning Differential Operators for Interpretable Time Series Modeling

no code implementations3 Sep 2022 Yingtao Luo, Chang Xu, Yang Liu, Weiqing Liu, Shun Zheng, Jiang Bian

In this work, we propose an learning framework that can automatically obtain interpretable PDE models from sequential data.

Decision Making Meta-Learning +1

Joint Beamforming Design for Intelligent Omni Surface Assisted Wireless Communication Systems

no code implementations1 Sep 2022 Wenhao Cai, Ming Li, Yang Liu, Qingqing Wu, Qian Liu

Intelligent reflecting surface (IRS) has been widely considered as one of the key enabling techniques for future wireless communication networks owing to its ability of dynamically controlling the phase shift of reflected electromagnetic (EM) waves to construct a favorable propagation environment.

Uncertainty-Induced Transferability Representation for Source-Free Unsupervised Domain Adaptation

1 code implementation30 Aug 2022 Jiangbo Pei, Zhuqing Jiang, Aidong Men, Liang Chen, Yang Liu, Qingchao Chen

Secondly, based on the UTR, we propose a novel Calibrated Adaption Framework (CAF) for SFUDA, including i)the source knowledge calibration module that guides the target model to learn the transferable source knowledge and discard the non-transferable one, and ii)the target semantics calibration module that calibrates the unreliable semantics.

Unsupervised Domain Adaptation

Conjugate Natural Selection: Fisher-Rao Natural Gradient Descent Optimally Approximates Evolutionary Dynamics and Continuous Bayesian Inference

no code implementations29 Aug 2022 Reilly Raab, Luca de Alfaro, Yang Liu

Rather than refining individual candidate solutions for a general non-convex optimization problem, by analogy to evolution, we consider minimizing the average loss for a parametric distribution over hypotheses.

Bayesian Inference

Delving into the Continuous Domain Adaptation

1 code implementation28 Aug 2022 Yinsong Xu, Zhuqing Jiang, Aidong Men, Yang Liu, Qingchao Chen

Existing domain adaptation methods assume that domain discrepancies are caused by a few discrete attributes and variations, e. g., art, real, painting, quickdraw, etc.

Domain Adaptation

Towards Communication Efficient and Fair Federated Personalized Sequential Recommendation

no code implementations23 Aug 2022 Sichun Luo, Yuanzhang Xiao, Yang Liu, Congduan Li, Linqi Song

Federated recommendations leverage the federated learning (FL) techniques to make privacy-preserving recommendations.

Fairness Federated Learning +2

I Know What You Do Not Know: Knowledge Graph Embedding via Co-distillation Learning

1 code implementation21 Aug 2022 Yang Liu, Zequn Sun, Guangyao Li, Wei Hu

To this end, we propose CoLE, a Co-distillation Learning method for KG Embedding that exploits the complementarity of graph structures and text information.

Knowledge Graph Embedding Language Modelling

Learning Program Representations with a Tree-Structured Transformer

no code implementations18 Aug 2022 Wenhan Wang, Kechi Zhang, Ge Li, Shangqing Liu, Anran Li, Zhi Jin, Yang Liu

Learning vector representations for programs is a critical step in applying deep learning techniques for program understanding tasks.

Representation Learning

CommitBART: A Large Pre-trained Model for GitHub Commits

no code implementations17 Aug 2022 Shangqing Liu, Yanzhou Li, Xiaofei Xie, Yang Liu

GitHub commits, which record the code changes with natural language messages for description, play a critical role for software developers to comprehend the software evolution.

Contrastive Learning Denoising

Defense against Backdoor Attacks via Identifying and Purifying Bad Neurons

no code implementations13 Aug 2022 Mingyuan Fan, Yang Liu, Cen Chen, Ximeng Liu, Wenzhong Guo

The opacity of neural networks leads their vulnerability to backdoor attacks, where hidden attention of infected neurons is triggered to override normal predictions to the attacker-chosen ones.

backdoor defense

Conditional Antibody Design as 3D Equivariant Graph Translation

1 code implementation12 Aug 2022 Xiangzhe Kong, Wenbing Huang, Yang Liu

Specifically, the relative improvement to baselines is about 23% in antigen-binding CDR design and 34% for affinity optimization.


Seeing your sleep stage: cross-modal distillation from EEG to infrared video

1 code implementation11 Aug 2022 Jianan Han, Shaoxing Zhang, Aidong Men, Yang Liu, Ziming Yao, Yan Yan, Qingchao Chen

$S^3VE$ is a large-scale dataset including synchronized infrared video and EEG signal for sleep stage classification, including 105 subjects and 154, 573 video clips that is more than 1100 hours long.

Electroencephalogram (EEG)

Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentation

1 code implementation9 Aug 2022 ChunYu Sun, Xin Tong, Yang Liu

Our method exploits semantic segmentation to fuse nonlocal instance features, such as center prediction, and further enhances the fusion scheme in a multi- and cross-level way.

3D Instance Segmentation 3D Part Segmentation +1

A Systematic Evaluation of Response Selection for Open Domain Dialogue

no code implementations SIGDIAL (ACL) 2022 Behnam Hedayatnia, Di Jin, Yang Liu, Dilek Hakkani-Tur

In this work, we curated a dataset where responses from multiple response generators produced for the same dialog context are manually annotated as appropriate (positive) and inappropriate (negative).

DialogSum Challenge: Results of the Dialogue Summarization Shared Task

1 code implementation8 Aug 2022 Yulong Chen, Naihao Deng, Yang Liu, Yue Zhang

We report the results of DialogSum Challenge, the shared task on summarizing real-life scenario dialogues at INLG 2022.

Joint Beamforming Design for RIS-Assisted Integrated Sensing and Communication Systems

no code implementations3 Aug 2022 Honghao Luo, Rang Liu, Ming Li, Yang Liu, Qian Liu

Integrated sensing and communication (ISAC) has been envisioned as a promising technology to tackle the spectrum congestion problem for future networks.

Physics-informed Deep Super-resolution for Spatiotemporal Data

1 code implementation2 Aug 2022 Pu Ren, Chengping Rao, Yang Liu, Zihan Ma, Qi Wang, Jian-Xun Wang, Hao Sun

High-fidelity simulation of complex physical systems is exorbitantly expensive and inaccessible across spatiotemporal scales.


Some Practice for Improving the Search Results of E-commerce

1 code implementation30 Jul 2022 Fanyou Wu, Yang Liu, Rado Gazo, Benes Bedrich, Xiaobo Qu

In the Amazon KDD Cup 2022, we aim to apply natural language processing methods to improve the quality of search results that can significantly enhance user experience and engagement with search engines for e-commerce.

Learning Prototype via Placeholder for Zero-shot Recognition

1 code implementation29 Jul 2022 Zaiquan Yang, Yang Liu, Wenjia Xu, Chong Huang, Lei Zhou, Chao Tong

Specifically, we combine seen classes to hallucinate new classes which play as placeholders of the unseen classes in the visual and semantic space.

Zero-Shot Learning

Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering

no code implementations26 Jul 2022 Yang Liu, Guanbin Li, Liang Lin

Existing visual question answering methods tend to capture the cross-modal spurious correlations, and fail to discover the true causal mechanism that facilitates reasoning truthfully based on the dominant visual evidence and the question intention.

Causal Inference Question Answering +3

Improving Bot Response Contradiction Detection via Utterance Rewriting

1 code implementation SIGDIAL (ACL) 2022 Di Jin, Sijia Liu, Yang Liu, Dilek Hakkani-Tur

Previous work has treated contradiction detection in bot responses as a task similar to natural language inference, e. g., detect the contradiction between a pair of bot utterances.

Natural Language Inference

Visible and Near Infrared Image Fusion Based on Texture Information

no code implementations22 Jul 2022 Guanyu Zhang, Beichen Sun, Yuehan Qi, Yang Liu

Multi-sensor fusion is widely used in the environment perception system of the autonomous vehicle.

Energy-Motivated Equivariant Pretraining for 3D Molecular Graphs

2 code implementations18 Jul 2022 Rui Jiao, Jiaqi Han, Wenbing Huang, Yu Rong, Yang Liu

Pretraining molecular representation models without labels is fundamental to various applications.

FedHAP: Federated Hashing with Global Prototypes for Cross-silo Retrieval

no code implementations12 Jul 2022 Meilin Yang, Jian Xu, Yang Liu, Wenbo Ding

To overcome these challenges, we propose a novel federated hashing framework that enables participating clients to jointly train the shared deep hashing model by leveraging the prototypical hash codes for each class.

Federated Learning Retrieval

Team PKU-WICT-MIPL PIC Makeup Temporal Video Grounding Challenge 2022 Technical Report

no code implementations6 Jul 2022 Minghang Zheng, Dejie Yang, Zhongjie Ye, Ting Lei, Yuxin Peng, Yang Liu

In this technical report, we briefly introduce the solutions of our team `PKU-WICT-MIPL' for the PIC Makeup Temporal Video Grounding (MTVG) Challenge in ACM-MM 2022.

Temporal Localization Video Grounding

Dynamic Contrastive Distillation for Image-Text Retrieval

no code implementations4 Jul 2022 Jun Rao, Liang Ding, Shuhan Qi, Meng Fang, Yang Liu, Li Shen, DaCheng Tao

Although the vision-and-language pretraining (VLP) equipped cross-modal image-text retrieval (ITR) has achieved remarkable progress in the past two years, it suffers from a major drawback: the ever-increasing size of VLP models restricts its deployment to real-world search scenarios (where the high latency is unacceptable).

Contrastive Learning Metric Learning +3

Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN

1 code implementation30 Jun 2022 Kuan Li, Yang Liu, Xiang Ao, Jianfeng Chi, Jinghua Feng, Hao Yang, Qing He

However, both strategies are faced with some immediate problems: raw features cannot represent various properties of nodes (e. g., structure information), and representations learned by supervised GNN may suffer from the poor performance of the classifier on the poisoned graph.

Understanding Instance-Level Impact of Fairness Constraints

1 code implementation30 Jun 2022 Jialu Wang, Xin Eric Wang, Yang Liu

A variety of fairness constraints have been proposed in the literature to mitigate group-level statistical bias.


Video Activity Localisation with Uncertainties in Temporal Boundary

no code implementations26 Jun 2022 Jiabo Huang, Hailin Jin, Shaogang Gong, Yang Liu

Such uncertainties in temporal labelling are currently ignored in model training, resulting in learning mis-matched video-text correlation with poor generalisation in test.

SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation

1 code implementation24 Jun 2022 Xin-Yang Zheng, Yang Liu, Peng-Shuai Wang, Xin Tong

We further complement the evaluation metrics of 3D generative models with the shading-image-based Fr\'echet inception distance (FID) scores to better assess visual quality and shape distribution of the generated shapes.

3D Shape Generation 3D Shape Representation

FedSSO: A Federated Server-Side Second-Order Optimization Algorithm

no code implementations20 Jun 2022 Xin Ma, Renyi Bao, Jinpeng Jiang, Yang Liu, Arthur Jiang, Jun Yan, Xin Liu, Zhisong Pan

In this work, we propose FedSSO, a server-side second-order optimization method for federated learning (FL).

Federated Learning

Enhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphs

no code implementations15 Jun 2022 Sha Li, Mahdi Namazifar, Di Jin, Mohit Bansal, Heng Ji, Yang Liu, Dilek Hakkani-Tur

Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging.

Multi-Task Learning Response Generation

Metric-Fair Classifier Derandomization

no code implementations15 Jun 2022 Jimmy Wu, Yatong Chen, Yang Liu

We study the problem of classifier derandomization in machine learning: given a stochastic binary classifier $f: X \to [0, 1]$, sample a deterministic classifier $\hat{f}: X \to \{0, 1\}$ that approximates the output of $f$ in aggregate over any data distribution.


To Aggregate or Not? Learning with Separate Noisy Labels

no code implementations14 Jun 2022 Jiaheng Wei, Zhaowei Zhu, Tianyi Luo, Ehsan Amid, Abhishek Kumar, Yang Liu

The rawly collected training data often comes with separate noisy labels collected from multiple imperfect annotators (e. g., via crowdsourcing).

Learning with noisy labels

AS2T: Arbitrary Source-To-Target Adversarial Attack on Speaker Recognition Systems

no code implementations7 Jun 2022 Guangke Chen, Zhe Zhao, Fu Song, Sen Chen, Lingling Fan, Yang Liu

Recent work has illuminated the vulnerability of speaker recognition systems (SRSs) against adversarial attacks, raising significant security concerns in deploying SRSs.

Adversarial Attack Speaker Recognition

Efficient and Accurate Physics-aware Multiplex Graph Neural Networks for 3D Small Molecules and Macromolecule Complexes

no code implementations6 Jun 2022 Shuo Zhang, Yang Liu, Lei Xie

Recent advances in applying Graph Neural Networks (GNNs) to molecular science have showcased the power of learning three-dimensional (3D) structure representations with GNNs.

Hybrid Models for Mixed Variables in Bayesian Optimization

no code implementations3 Jun 2022 Hengrui Luo, Younghyun Cho, James W. Demmel, Xiaoye S. Li, Yang Liu

We systematically describe the problem of simultaneous surrogate modeling of mixed variables (i. e., continuous, integer and categorical variables) in the Bayesian optimization (BO) context.

Gaussian Processes Model Selection

Multi-stage Moving Target Defense: A Security-enhanced D-FACTS Implementation Approach

no code implementations2 Jun 2022 Jiazhou Wang, Jue Tian, Yang Liu, Xiaohong Guan, Dong Yang, Ting Liu

We prove that a designed MMTD can significantly improve the detection capability compared to existing one-stage MTDs.

Fairness Transferability Subject to Bounded Distribution Shift

1 code implementation31 May 2022 Yatong Chen, Reilly Raab, Jialu Wang, Yang Liu

Given an algorithmic predictor that is "fair" on some source distribution, will it still be fair on an unknown target distribution that differs from the source within some bound?

BIG-bench Machine Learning Fairness

Certifying Some Distributional Fairness with Subpopulation Decomposition

1 code implementation31 May 2022 Mintong Kang, Linyi Li, Maurice Weber, Yang Liu, Ce Zhang, Bo Li

In this paper, we first formulate the certified fairness of an ML model trained on a given data distribution as an optimization problem based on the model performance loss bound on a fairness constrained distribution, which is within bounded distributional distance with the training distribution.


ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generation

1 code implementation29 May 2022 Haoxiang Guo, Shilin Liu, Hao Pan, Yang Liu, Xin Tong, Baining Guo

We view the reconstruction of CAD models in the boundary representation (B-Rep) as the detection of geometric primitives of different orders, i. e. vertices, edges and surface patches, and the correspondence of primitives, which are holistically modeled as a chain complex, and show that by modeling such comprehensive structures more complete and regularized reconstructions can be achieved.

GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis

no code implementations27 May 2022 Yushi Cao, Zhiming Li, Tianpei Yang, Hao Zhang, Yan Zheng, Yi Li, Jianye Hao, Yang Liu

In this paper, we combine the above two paradigms together and propose a novel Generalizable Logic Synthesis (GALOIS) framework to synthesize hierarchical and strict cause-effect logic programs.

Decision Making Program Synthesis +2

Decoupled Pyramid Correlation Network for Liver Tumor Segmentation from CT images

no code implementations26 May 2022 Yao Zhang, Jiawei Yang, Yang Liu, Jiang Tian, Siyun Wang, Cheng Zhong, Zhongchao shi, Yang Zhang, Zhiqiang He

In this paper, we propose a Decoupled Pyramid Correlation Network (DPC-Net) that exploits attention mechanisms to fully leverage both low- and high-level features embedded in FCN to segment liver tumor.

Computed Tomography (CT) Image Segmentation +2

Symbolic Physics Learner: Discovering governing equations via Monte Carlo tree search

no code implementations26 May 2022 Fangzheng Sun, Yang Liu, Jian-Xun Wang, Hao Sun

The key concept is to interpret mathematical operations and system state variables by computational rules and symbols, establish symbolic reasoning of mathematical formulas via expression trees, and employ a Monte Carlo tree search (MCTS) agent to explore optimal expression trees based on measurement data.

A Template-based Method for Constrained Neural Machine Translation

1 code implementation23 May 2022 Shuo Wang, Peng Li, Zhixing Tan, Zhaopeng Tu, Maosong Sun, Yang Liu

In this work, we propose a template-based method that can yield results with high translation quality and match accuracy and the inference speed of our method is comparable with unconstrained NMT models.

Machine Translation NMT +1

Directed Acyclic Transformer for Non-Autoregressive Machine Translation

1 code implementation16 May 2022 Fei Huang, Hao Zhou, Yang Liu, Hang Li, Minlie Huang

Non-autoregressive Transformers (NATs) significantly reduce the decoding latency by generating all tokens in parallel.

Knowledge Distillation Machine Translation +1

PrEF: Percolation-based Evolutionary Framework for the diffusion-source-localization problem in large networks

no code implementations16 May 2022 Yang Liu, Xiaoqi Wang, Xi Wang, Zhen Wang, Jürgen Kurths

We assume that the state of a number of nodes in a network could be investigated if necessary, and study what configuration of those nodes could facilitate a better solution for the diffusion-source-localization (DSL) problem.

Residue-based Label Protection Mechanisms in Vertical Logistic Regression

no code implementations9 May 2022 Juntao Tan, Lan Zhang, Yang Liu, Anran Li, Ye Wu

To deal with this, we then propose three protection mechanisms, e. g., additive noise mechanism, multiplicative noise mechanism, and hybrid mechanism which leverages local differential privacy and homomorphic encryption techniques, to prevent the attack and improve the robustness of the vertical logistic regression.

Federated Learning Inference Attack +1

Investigating Generalization by Controlling Normalized Margin

1 code implementation8 May 2022 Alexander R. Farhang, Jeremy Bernstein, Kushal Tirumala, Yang Liu, Yisong Yue

Weight norm $\|w\|$ and margin $\gamma$ participate in learning theory via the normalized margin $\gamma/\|w\|$.

Learning Theory

Mixed-UNet: Refined Class Activation Mapping for Weakly-Supervised Semantic Segmentation with Multi-scale Inference

no code implementations6 May 2022 Yang Liu, Ersi Zhang, Lulu Xu, Chufan Xiao, Xiaoyun Zhong, Lijin Lian, Fang Li, Bin Jiang, Yuhan Dong, Lan Ma, Qiming Huang, Ming Xu, Yongbing Zhang, Dongmei Yu, Chenggang Yan, Peiwu Qin

Deep learning techniques have shown great potential in medical image processing, particularly through accurate and reliable image segmentation on magnetic resonance imaging (MRI) scans or computed tomography (CT) scans, which allow the localization and diagnosis of lesions.

Computed Tomography (CT) Image Segmentation +2