Search Results for author: Ke Xu

Found 116 papers, 48 papers with code

Graph Neural Ordinary Differential Equations-based method for Collaborative Filtering

no code implementations21 Nov 2023 Ke Xu, Yuanjie Zhu, Weizhi Zhang, Philip S. Yu

This inspired us to address the computational limitations of GCN-based models by designing a simple and efficient NODE-based model that can skip some GCN layers to reach the final state, thus avoiding the need to create many layers.

Collaborative Filtering

Robust NOMA-assisted OTFS-ISAC Network Design with 3D Motion Prediction Topology

no code implementations21 Oct 2023 Luping Xiang, Ke Xu, Jie Hu, Christos Masouros, Kun Yang

This paper proposes a novel non-orthogonal multiple access (NOMA)-assisted orthogonal time-frequency space (OTFS)-integrated sensing and communication (ISAC) network, which uses unmanned aerial vehicles (UAVs) as air base stations to support multiple users.

Fairness motion prediction

Green Beamforming Design for Integrated Sensing and Communication Systems: A Practical Approach Using Beam-Matching Error Metrics

no code implementations21 Oct 2023 Luping Xiang, Ke Xu, Jie Hu, Kun Yang

In this paper, we propose a green beamforming design for the integrated sensing and communication (ISAC) system, using beam-matching error to assess radar performance.

Antenna Response Consistency Driven Self-supervised Learning for WIFI-based Human Activity Recognition

no code implementations10 Oct 2023 Ke Xu, Jiangtao Wang, Hongyuan Zhu, Dingchang Zheng

We attribute this issue to the inappropriate alignment criteria, which disrupt the semantic distance consistency between the feature space and the input space.

Contrastive Learning Human Activity Recognition +1

RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models

1 code implementation1 Oct 2023 Zekun Moore Wang, Zhongyuan Peng, Haoran Que, Jiaheng Liu, Wangchunshu Zhou, Yuhan Wu, Hongcheng Guo, Ruitong Gan, Zehao Ni, Man Zhang, Zhaoxiang Zhang, Wanli Ouyang, Ke Xu, Wenhu Chen, Jie Fu, Junran Peng

The advent of Large Language Models (LLMs) has paved the way for complex tasks such as role-playing, which enhances user interactions by enabling models to imitate various characters.


Large Language Model for Science: A Study on P vs. NP

1 code implementation11 Sep 2023 Qingxiu Dong, Li Dong, Ke Xu, Guangyan Zhou, Yaru Hao, Zhifang Sui, Furu Wei

In this work, we use large language models (LLMs) to augment and accelerate research on the P versus NP problem, one of the most important open problems in theoretical computer science and mathematics.

Language Modelling Large Language Model

Referring Image Segmentation Using Text Supervision

1 code implementation ICCV 2023 Fang Liu, Yuhao Liu, Yuqiu Kong, Ke Xu, Lihe Zhang, BaoCai Yin, Gerhard Hancke, Rynson Lau

Hence, we propose a novel weakly-supervised RIS framework to formulate the target localization problem as a classification process to differentiate between positive and negative text expressions.

Image Segmentation Object Localization +4

EQ-Net: Elastic Quantization Neural Networks

1 code implementation ICCV 2023 Ke Xu, Lei Han, Ye Tian, Shangshang Yang, Xingyi Zhang

In this paper, we explore a one-shot network quantization regime, named Elastic Quantization Neural Networks (EQ-Net), which aims to train a robust weight-sharing quantization supernet.


Lighting up NeRF via Unsupervised Decomposition and Enhancement

1 code implementation ICCV 2023 Haoyuan Wang, Xiaogang Xu, Ke Xu, Rynson WH. Lau

Neural Radiance Field (NeRF) is a promising approach for synthesizing novel views, given a set of images and the corresponding camera poses of a scene.

Low-Light Image Enhancement

Self-Supervised Learning for WiFi CSI-Based Human Activity Recognition: A Systematic Study

no code implementations19 Jul 2023 Ke Xu, Jiangtao Wang, Hongyuan Zhu, Dingchang Zheng

Therefore, considerable efforts have been made to address the challenge of insufficient data in deep learning by leveraging SSL algorithms.

Human Activity Recognition Self-Supervised Learning

Pulse Shape-Aided Multipath Delay Estimation for Fine-Grained WiFi Sensing

no code implementations27 Jun 2023 Ke Xu, He Chen, Chenshu Wu

Considering the limited number of paths in physical environments, we formulate the multipath delay estimation as a sparse recovery problem.


RF-Based Simultaneous Localization and Source Seeking for Multi-Robot Systems

no code implementations27 Jun 2023 Ke Xu, Rui Zhang, He Chen

This paper considers a radio-frequency (RF)-based simultaneous localization and source-seeking (SLASS) problem in multi-robot systems, where multiple robots jointly localize themselves and an RF source using distance-only measurements extracted from RF signals and then control themselves to approach the source.

HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification

1 code implementation24 May 2023 He Zhu, Chong Zhang, JunJie Huang, Junran Wu, Ke Xu

Hierarchical text classification (HTC) is a challenging subtask of multi-label classification as the labels form a complex hierarchical structure.

Multi-Label Classification text-classification +1

Interactive Natural Language Processing

no code implementations22 May 2023 Zekun Wang, Ge Zhang, Kexin Yang, Ning Shi, Wangchunshu Zhou, Shaochun Hao, Guangzheng Xiong, Yizhi Li, Mong Yuan Sim, Xiuying Chen, Qingqing Zhu, Zhenzhu Yang, Adam Nik, Qi Liu, Chenghua Lin, Shi Wang, Ruibo Liu, Wenhu Chen, Ke Xu, Dayiheng Liu, Yike Guo, Jie Fu

Interactive Natural Language Processing (iNLP) has emerged as a novel paradigm within the field of NLP, aimed at addressing limitations in existing frameworks while aligning with the ultimate goals of artificial intelligence.

Decision Making

SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning

1 code implementation8 May 2023 Junran Wu, Xueyuan Chen, Bowen Shi, Shangzhe Li, Ke Xu

In contrastive learning, the choice of ``view'' controls the information that the representation captures and influences the performance of the model.

Contrastive Learning Graph Classification +1

Graph Collaborative Signals Denoising and Augmentation for Recommendation

1 code implementation6 Apr 2023 Ziwei Fan, Ke Xu, Zhang Dong, Hao Peng, Jiawei Zhang, Philip S. Yu

Moreover, we show that the inclusion of user-user and item-item correlations can improve recommendations for users with both abundant and insufficient interactions.

Collaborative Filtering Denoising +1

Deploying Offline Reinforcement Learning with Human Feedback

no code implementations13 Mar 2023 Ziniu Li, Ke Xu, Liu Liu, Lanqing Li, Deheng Ye, Peilin Zhao

To address this issue, we propose an alternative framework that involves a human supervising the RL models and providing additional feedback in the online deployment phase.

Decision Making Model Selection +3

SAT Requires Exhaustive Search

no code implementations19 Feb 2023 Ke Xu, Guangyan Zhou

In this paper, by constructing extremely hard examples of CSP (with large domains) and SAT (with long clauses), we prove that such examples cannot be solved without exhaustive search, which is stronger than P $\neq$ NP.

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 +3

Orthogonal-Time-Frequency-Space Signal Design for Integrated Data and Energy Transfer: Benefits from Doppler Offsets

no code implementations3 Feb 2023 Jie Hu, Ke Xu, Luping Xiang, Kun Yang

Integrated data and energy transfer (IDET) is an advanced technology for enabling energy sustainability for massively deployed low-power electronic consumption components.

MAKE: Vision-Language Pre-training based Product Retrieval in Taobao Search

no code implementations30 Jan 2023 Xiaoyang Zheng, Zilong Wang, Ke Xu, Sen Li, Tao Zhuang, Qingwen Liu, Xiaoyi Zeng

Given a user query, the retrieval phase returns a subset of candidate products for the following ranking phase.


DoubleH: Twitter User Stance Detection via Bipartite Graph Neural Networks

no code implementations20 Jan 2023 Chong Zhang, Zhenkun Zhou, Xingyu Peng, Ke Xu

Subsequently, we propose a bipartite graph neural network model, DoubleH, which aims to better utilize homogeneous and heterogeneous information in user stance detection tasks.

Stance Classification Stance Detection

Structure-Informed Shadow Removal Networks

no code implementations9 Jan 2023 Yuhao Liu, Qing Guo, Lan Fu, Zhanghan Ke, Ke Xu, Wei Feng, Ivor W. Tsang, Rynson W. H. Lau

Extensive experiments on three shadow removal benchmarks demonstrate that our method outperforms existing shadow removal methods, and our StructNet can be integrated with existing methods to boost their performances further.

Shadow Removal

Learning Image Harmonization in the Linear Color Space

no code implementations ICCV 2023 Ke Xu, Gerhard Petrus Hancke, Rynson W.H. Lau

In this paper, we propose a novel neural approach to harmonize the image colors in a camera-independent color space, in which color values are proportional to the scene radiance.

Image Harmonization

Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence

no code implementations ICCV 2023 Han Fang, Jiyi Zhang, Yupeng Qiu, Ke Xu, Chengfang Fang, Ee-Chien Chang

In this paper, we take the role of investigators who want to trace the attack and identify the source, that is, the particular model which the adversarial examples are generated from.

Adversarial Attack

Differentially Private Learning with Per-Sample Adaptive Clipping

no code implementations1 Dec 2022 Tianyu Xia, Shuheng Shen, Su Yao, Xinyi Fu, Ke Xu, Xiaolong Xu, Xing Fu

As one way to implement privacy-preserving AI, differentially private learning is a framework that enables AI models to use differential privacy (DP).

Privacy Preserving

Novel Modelling Strategies for High-frequency Stock Trading Data

no code implementations30 Nov 2022 Xuekui Zhang, Yuying Huang, Ke Xu, Li Xing

Full electronic automation in stock exchanges has recently become popular, generating high-frequency intraday data and motivating the development of near real-time price forecasting methods.

Feature Engineering Vocal Bursts Intensity Prediction

3D-QueryIS: A Query-based Framework for 3D Instance Segmentation

no code implementations17 Nov 2022 Jiaheng Liu, Tong He, Honghui Yang, Rui Su, Jiayi Tian, Junran Wu, Hongcheng Guo, Ke Xu, Wanli Ouyang

Previous top-performing methods for 3D instance segmentation often maintain inter-task dependencies and the tendency towards a lack of robustness.

3D Instance Segmentation Segmentation +1

Local Color Distributions Prior for Image Enhancement

2 code implementations ECCV 2022 Haoyuan Wang, Ke Xu, and Rynson W.H. Lau

Existing image enhancement methods are typically designed to address either the over- or under-exposure problem in the input image.

Low-Light Image Enhancement

Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation

no code implementations19 Oct 2022 Chengqian Gao, Ke Xu, Liu Liu, Deheng Ye, Peilin Zhao, Zhiqiang Xu

A promising paradigm for offline reinforcement learning (RL) is to constrain the learned policy to stay close to the dataset behaviors, known as policy constraint offline RL.

D4RL Offline RL +2

FedDef: Defense Against Gradient Leakage in Federated Learning-based Network Intrusion Detection Systems

no code implementations8 Oct 2022 Jiahui Chen, Yi Zhao, Qi Li, Xuewei Feng, Ke Xu

Deep learning (DL) methods have been widely applied to anomaly-based network intrusion detection system (NIDS) to detect malicious traffic.

Adversarial Attack Federated Learning +1

Boosting Night-time Scene Parsing with Learnable Frequency

1 code implementation30 Aug 2022 Zhifeng Xie, Sen Wang, Ke Xu, Zhizhong Zhang, Xin Tan, Yuan Xie, Lizhuang Ma

Based on this, we propose to exploit the image frequency distributions for night-time scene parsing.

Autonomous Driving Scene Parsing

Quantized Adaptive Subgradient Algorithms and Their Applications

no code implementations11 Aug 2022 Ke Xu, Jianqiao Wangni, Yifan Zhang, Deheng Ye, Jiaxiang Wu, Peilin Zhao

Therefore, a threshold quantization strategy with a relatively small error is adopted in QCMD adagrad and QRDA adagrad to improve the signal-to-noise ratio and preserve the sparsity of the model.


PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch

no code implementations5 Jul 2022 Ke Xu, Yao Xiao, Zhaoheng Zheng, Kaijie Cai, Ram Nevatia

Despite the diversity in attack patterns, adversarial patches tend to be highly textured and different in appearance from natural images.

Image Classification object-detection +3

Harmonizer: Learning to Perform White-Box Image and Video Harmonization

2 code implementations4 Jul 2022 Zhanghan Ke, Chunyi Sun, Lei Zhu, Ke Xu, Rynson W. H. Lau

Unlike prior methods that are based on black-box autoencoders, Harmonizer contains a neural network for filter argument prediction and several white-box filters (based on the predicted arguments) for image harmonization.

Image Harmonization Video Harmonization

Structural Entropy Guided Graph Hierarchical Pooling

1 code implementation26 Jun 2022 Junran Wu, Xueyuan Chen, Ke Xu, Shangzhe Li

In addition to SEP, we further design two classification models, SEP-G and SEP-N for graph classification and node classification, respectively.

Graph Classification Node Classification

A Simple yet Effective Method for Graph Classification

1 code implementation6 Jun 2022 Junran Wu, Shangzhe Li, Jianhao Li, YiCheng Pan, Ke Xu

Inspired by structural entropy on graphs, we transform the data sample from graphs to coding trees, which is a simpler but essential structure for graph data.

Graph Classification

CoupleFace: Relation Matters for Face Recognition Distillation

no code implementations12 Apr 2022 Jiaheng Liu, Haoyu Qin, Yichao Wu, Jinyang Guo, Ding Liang, Ke Xu

In this work, we observe that mutual relation knowledge between samples is also important to improve the discriminative ability of the learned representation of the student model, and propose an effective face recognition distillation method called CoupleFace by additionally introducing the Mutual Relation Distillation (MRD) into existing distillation framework.

Face Recognition Knowledge Distillation

Bi-directional Object-context Prioritization Learning for Saliency Ranking

1 code implementation CVPR 2022 Xin Tian, Ke Xu, Xin Yang, Lin Du, BaoCai Yin, Rynson W. H. Lau

We observe that spatial attention works concurrently with object-based attention in the human visual recognition system.

Saliency Ranking

Interactive Data Analysis with Next-step Natural Language Query Recommendation

1 code implementation13 Jan 2022 Xingbo Wang, Furui Cheng, Yong Wang, Ke Xu, Jiang Long, Hong Lu, Huamin Qu

Natural language interfaces (NLIs) provide users with a convenient way to interactively analyze data through natural language queries.

Natural Language Queries

Adaptive Channel Encoding Transformer for Point Cloud Analysis

no code implementations5 Dec 2021 Guoquan Xu, Hezhi Cao, Yifan Zhang, Yanxin Ma, Jianwei Wan, Ke Xu

Transformer plays an increasingly important role in various computer vision areas and remarkable achievements have also been made in point cloud analysis.

Point Cloud Classification

Adaptive Channel Encoding for Point Cloud Analysis

no code implementations5 Dec 2021 Guoquan Xu, Hezhi Cao, Yifan Zhang, Jianwei Wan, Ke Xu, Yanxin Ma

Attention mechanism plays a more and more important role in point cloud analysis and channel attention is one of the hotspots.

Geometry-aware Two-scale PIFu Representation for Human Reconstruction

no code implementations3 Dec 2021 Zheng Dong, Ke Xu, Ziheng Duan, Hujun Bao, Weiwei Xu, Rynson W. H. Lau

Our key idea is to exploit the complementary properties of depth denoising and 3D reconstruction, for learning a two-scale PIFu representation to reconstruct high-frequency facial details and consistent bodies separately.

3D Human Reconstruction 3D Reconstruction +3

Mitigating Adversarial Attacks by Distributing Different Copies to Different Users

no code implementations30 Nov 2021 Jiyi Zhang, Han Fang, Wesley Joon-Wie Tann, Ke Xu, Chengfang Fang, Ee-Chien Chang

We point out that by distributing different copies of the model to different buyers, we can mitigate the attack such that adversarial samples found on one copy would not work on another copy.

Gait Identification under Surveillance Environment based on Human Skeleton

no code implementations23 Nov 2021 Xingkai Zheng, Xirui Li, Ke Xu, Xinghao Jiang, Tanfeng Sun

Most existing gait identification methods extract features from gait videos and identify a probe sample by a query in the gallery.

Gait Identification

Learning to Detect Instance-level Salient Objects Using Complementary Image Labels

no code implementations19 Nov 2021 Xin Tian, Ke Xu, Xin Yang, BaoCai Yin, Rynson W. H. Lau

However, it is non-trivial to use only class labels to learn instance-aware saliency information, as salient instances with high semantic affinities may not be easily separated by the labels.

Boundary Detection Object Localization +1

Value Penalized Q-Learning for Recommender Systems

no code implementations15 Oct 2021 Chengqian Gao, Ke Xu, Kuangqi Zhou, Lanqing Li, Xueqian Wang, Bo Yuan, Peilin Zhao

To alleviate the action distribution shift problem in extracting RL policy from static trajectories, we propose Value Penalized Q-learning (VPQ), an uncertainty-based offline RL algorithm.

Offline RL Q-Learning +2

Hierarchical information matters: Text classification via tree based graph neural network

2 code implementations COLING 2022 Chong Zhang, He Zhu, Xingyu Peng, Junran Wu, Ke Xu

Inspired by the structural entropy, we construct the coding tree of the graph by minimizing the structural entropy and propose HINT, which aims to make full use of the hierarchical information contained in the text for the task of text classification.

Dependency Parsing text-classification +1

Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression

1 code implementation EMNLP 2021 Canwen Xu, Wangchunshu Zhou, Tao Ge, Ke Xu, Julian McAuley, Furu Wei

Recent studies on compression of pretrained language models (e. g., BERT) usually use preserved accuracy as the metric for evaluation.

Knowledge Distillation Quantization

Structural Optimization Makes Graph Classification Simpler and Better

1 code implementation5 Sep 2021 Junran Wu, Jianhao Li, YiCheng Pan, Ke Xu

We then present an implementation of the scheme in a tree kernel and a convolutional network to perform graph classification.

Graph Classification

Dual-Neighborhood Deep Fusion Network for Point Cloud Analysis

no code implementations20 Aug 2021 Guoquan Xu, Hezhi Cao, Yifan Zhang, Jianwei Wan, Ke Xu, Yanxin Ma

To handle this prob-lem, a feature representation learning method, named Dual-Neighborhood Deep Fusion Network (DNDFN), is proposed to serve as an improved point cloud encoder for the task of non-idealized point cloud classification.

3D Point Cloud Classification Classification +2

Realtime Robust Malicious Traffic Detection via Frequency Domain Analysis

1 code implementation28 Jun 2021 Chuanpu Fu, Qi Li, Meng Shen, Ke Xu

To this end, we propose Whisper, a realtime ML based malicious traffic detection system that achieves both high accuracy and high throughput by utilizing frequency domain features.

AdaptCL: Efficient Collaborative Learning with Dynamic and Adaptive Pruning

no code implementations27 Jun 2021 Guangmeng Zhou, Ke Xu, Qi Li, Yang Liu, Yi Zhao

In a highly heterogeneous environment, AdaptCL achieves a training speedup of 6. 2x with a slight loss of accuracy.

Learning to Sample Replacements for ELECTRA Pre-Training

no code implementations Findings (ACL) 2021 Yaru Hao, Li Dong, Hangbo Bao, Ke Xu, Furu Wei

Moreover, we propose to use a focal loss for the generator in order to relieve oversampling of correct tokens as replacements.

Language Modelling Masked Language Modeling

Price graphs: Utilizing the structural information of financial time series for stock prediction

1 code implementation4 Jun 2021 Junran Wu, Ke Xu, Xueyuan Chen, Shangzhe Li, Jichang Zhao

Then, structural information, referring to associations among temporal points and the node weights, is extracted from the mapped graphs to resolve the problems regarding long-range dependencies and the chaotic property.

Stock Prediction Time Series +1

Exploring Memorization in Adversarial Training

1 code implementation ICLR 2022 Yinpeng Dong, Ke Xu, Xiao Yang, Tianyu Pang, Zhijie Deng, Hang Su, Jun Zhu

In this paper, we explore the memorization effect in adversarial training (AT) for promoting a deeper understanding of model capacity, convergence, generalization, and especially robust overfitting of the adversarially trained models.


Voice2Mesh: Cross-Modal 3D Face Model Generation from Voices

1 code implementation21 Apr 2021 Cho-Ying Wu, Ke Xu, Chin-Cheng Hsu, Ulrich Neumann

This work focuses on the analysis that whether 3D face models can be learned from only the speech inputs of speakers.

Face Generation Face Model +1

Excited state fluid mechanics and mathematical principles of separation and transition

no code implementations6 Jan 2021 Peng Yue, Jingping Xiao, Ke Xu, Yiyu Lu, Dewei Peng

Hitherto, separation and transition problems have not been described accurately in mathematical terms, leading to design errors and prediction problems in fluid machine engineering.

Fluid Dynamics

Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting

1 code implementation EMNLP 2021 Wangchunshu Zhou, Tao Ge, Canwen Xu, Ke Xu, Furu Wei

In this paper, we generalize text infilling (e. g., masked language models) by proposing Sequence Span Rewriting (SSR) as a self-supervised sequence-to-sequence (seq2seq) pre-training objective.

Text Infilling

Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting

no code implementations ICCV 2021 Lei Zhu, Ke Xu, Zhanghan Ke, Rynson W.H. Lau

These two phenomenons reveal that deep shadow detectors heavily depend on the intensity cue, which we refer to as intensity bias.

Shadow Detection

Improving BERT with Syntax-aware Local Attention

1 code implementation Findings (ACL) 2021 Zhongli Li, Qingyu Zhou, Chao Li, Ke Xu, Yunbo Cao

Pre-trained Transformer-based neural language models, such as BERT, have achieved remarkable results on varieties of NLP tasks.

Machine Translation Question Answering +2

Location-aware Single Image Reflection Removal

1 code implementation ICCV 2021 Zheng Dong, Ke Xu, Yin Yang, Hujun Bao, Weiwei Xu, Rynson W. H. Lau

It is beneficial to strong reflection detection and substantially improves the quality of reflection removal results.

Reflection Removal

GDA-HIN: A Generalized Domain Adaptive Model across Heterogeneous Information Networks

no code implementations10 Dec 2020 Tiancheng Huang, Ke Xu, Donglin Wang

Domain adaptation using graph-structured networks learns label-discriminative and network-invariant node embeddings by sharing graph parameters.

Domain Adaptation Transfer Learning

Investigating Learning Dynamics of BERT Fine-Tuning

no code implementations Asian Chapter of the Association for Computational Linguistics 2020 Yaru Hao, Li Dong, Furu Wei, Ke Xu

The recently introduced pre-trained language model BERT advances the state-of-the-art on many NLP tasks through the fine-tuning approach, but few studies investigate how the fine-tuning process improves the model performance on downstream tasks.

Language Modelling

Robust Attacks on Deep Learning Face Recognition in the Physical World

no code implementations27 Nov 2020 Meng Shen, Hao Yu, Liehuang Zhu, Ke Xu, Qi Li, Xiaojiang Du

Deep neural networks (DNNs) have been increasingly used in face recognition (FR) systems.

Face Recognition

Exact Phase Transitions of Model RB with Slower-Growing Domains

no code implementations5 Nov 2020 Jun Liu, Ke Xu, Guangyan Zhou

The second moment method has always been an effective tool to lower bound the satisfiability threshold of many random constraint satisfaction problems.

Weakly-supervised Salient Instance Detection

no code implementations29 Sep 2020 Xin Tian, Ke Xu, Xin Yang, Bao-Cai Yin, Rynson W. H. Lau

Inspired by this insight, we propose to use class and subitizing labels as weak supervision for the SID problem.

Boundary Detection Object Localization +1

Towards Ground Truth Explainability on Tabular Data

1 code implementation20 Jul 2020 Brian Barr, Ke Xu, Claudio Silva, Enrico Bertini, Robert Reilly, C. Bayan Bruss, Jason D. Wittenbach

In data science, there is a long history of using synthetic data for method development, feature selection and feature engineering.

Feature Engineering feature selection

Relation-Aware Transformer for Portfolio Policy Learning

2 code implementations IJCAI 2020 Ke Xu, Yifan Zhang, Deheng Ye, Peilin Zhao, Mingkui Tan

One of the key issues is how to represent the non-stationary price series of assets in a portfolio, which is important for portfolio decisions.

BERT Loses Patience: Fast and Robust Inference with Early Exit

1 code implementation NeurIPS 2020 Wangchunshu Zhou, Canwen Xu, Tao Ge, Julian McAuley, Ke Xu, Furu Wei

In this paper, we propose Patience-based Early Exit, a straightforward yet effective inference method that can be used as a plug-and-play technique to simultaneously improve the efficiency and robustness of a pretrained language model (PLM).

Language Modelling

Learning to Restore Low-Light Images via Decomposition-and-Enhancement

no code implementations CVPR 2020 Ke Xu, Xin Yang, Baocai Yin, Rynson W.H. Lau

While concurrently enhancing a low-light image and removing its noise is ill-posed, we observe that noise exhibits different levels of contrast in different frequency layers, and it is much easier to detect noise in the lowfrequency layer than in the high one.

Low-Light Image Enhancement

Synchrotron Microtomography and Neutron Radiography Characterization of the Microstruture and Water Absorption of Concrete from Pompeii

no code implementations27 May 2020 Ke Xu, Anton S. Tremsin, Jiaqi Li, Daniela M. Ushizima, Catherine A. Davy, Amine Bouterf, Ying Tsun Su, Milena Marroccoli, Anna Maria Mauro, Massimo Osanna, Antonio Telesca, Paulo J. M. Monteiro

In the present work, samples were drilled from the "Hospitium" in Pompeii and were analyzed by synchrotron microtomography (uCT) and neutron radiography to study how the microstructure, including the presence of induced cracks, affects their water adsorption.

Applied Physics Materials Science Geophysics

Harvesting and Refining Question-Answer Pairs for Unsupervised QA

1 code implementation ACL 2020 Zhongli Li, Wenhui Wang, Li Dong, Furu Wei, Ke Xu

Our approach outperforms previous unsupervised approaches by a large margin and is competitive with early supervised models.

Few-Shot Learning Question Answering

Scheduled DropHead: A Regularization Method for Transformer Models

1 code implementation Findings of the Association for Computational Linguistics 2020 Wangchunshu Zhou, Tao Ge, Ke Xu, Furu Wei, Ming Zhou

In this paper, we introduce DropHead, a structured dropout method specifically designed for regularizing the multi-head attention mechanism, which is a key component of transformer, a state-of-the-art model for various NLP tasks.

Machine Translation text-classification +2

Self-Attention Attribution: Interpreting Information Interactions Inside Transformer

2 code implementations23 Apr 2020 Yaru Hao, Li Dong, Furu Wei, Ke Xu

The great success of Transformer-based models benefits from the powerful multi-head self-attention mechanism, which learns token dependencies and encodes contextual information from the input.

Night-time Scene Parsing with a Large Real Dataset

no code implementations15 Mar 2020 Xin Tan, Ke Xu, Ying Cao, Yiheng Zhang, Lizhuang Ma, Rynson W. H. Lau

Although huge progress has been made on scene analysis in recent years, most existing works assume the input images to be in day-time with good lighting conditions.

Scene Parsing Semantic Segmentation

Learning to Compare for Better Training and Evaluation of Open Domain Natural Language Generation Models

no code implementations12 Feb 2020 Wangchunshu Zhou, Ke Xu

While able to be trained in a fully self-supervised fashion, our model can be further fine-tuned with a little amount of human preference annotation to better imitate human judgment.

Natural Language Understanding Response Generation +1

Pseudo-Bidirectional Decoding for Local Sequence Transduction

no code implementations Findings of the Association for Computational Linguistics 2020 Wangchunshu Zhou, Tao Ge, Ke Xu

PBD copies the corresponding representation of source tokens to the decoder as pseudo future context to enable the decoder to attends to its bi-directional context.

Grammatical Error Correction Inductive Bias +1

Self-Adversarial Learning with Comparative Discrimination for Text Generation

no code implementations ICLR 2020 Wangchunshu Zhou, Tao Ge, Ke Xu, Furu Wei, Ming Zhou

Conventional Generative Adversarial Networks (GANs) for text generation tend to have issues of reward sparsity and mode collapse that affect the quality and diversity of generated samples.

Text Generation

Improving Grammatical Error Correction with Machine Translation Pairs

1 code implementation Findings of the Association for Computational Linguistics 2020 Wangchunshu Zhou, Tao Ge, Chang Mu, Ke Xu, Furu Wei, Ming Zhou

The poor translation model resembles the ESL (English as a second language) learner and tends to generate translations of low quality in terms of fluency and grammatical correctness, while the good translation model generally generates fluent and grammatically correct translations.

Grammatical Error Correction Language Modelling +2

Personalized Graph Neural Networks with Attention Mechanism for Session-Aware Recommendation

3 code implementations20 Oct 2019 Mengqi Zhang, Shu Wu, Meng Gao, Xin Jiang, Ke Xu, Liang Wang

The other is Dot-Product Attention mechanism, which draws on the Transformer net to explicitly model the effect of historical sessions on the current session.

Machine Translation Session-Based Recommendations

Online monitoring for safe pedestrian-vehicle interactions

no code implementations12 Oct 2019 Peter Du, Zhe Huang, Tianqi Liu, Ke Xu, Qichao Gao, Hussein Sibai, Katherine Driggs-Campbell, Sayan Mitra

As autonomous systems begin to operate amongst humans, methods for safe interaction must be investigated.

Test Robotics Multiagent Systems Signal Processing

Where Is My Mirror?

1 code implementation ICCV 2019 Xin Yang, Haiyang Mei, Ke Xu, Xiaopeng Wei, Bao-Cai Yin, Rynson W. H. Lau

To the best of our knowledge, this is the first work to address the mirror segmentation problem with a computational approach.


DRFN: Deep Recurrent Fusion Network for Single-Image Super-Resolution with Large Factors

no code implementations23 Aug 2019 Xin Yang, Haiyang Mei, Jiqing Zhang, Ke Xu, Bao-Cai Yin, Qiang Zhang, Xiaopeng Wei

Recently, single-image super-resolution has made great progress owing to the development of deep convolutional neural networks (CNNs).

Image Super-Resolution

Visualizing and Understanding the Effectiveness of BERT

no code implementations IJCNLP 2019 Yaru Hao, Li Dong, Furu Wei, Ke Xu

Language model pre-training, such as BERT, has achieved remarkable results in many NLP tasks.

Language Modelling

Multi-Level Order-Flow Imbalance in a Limit Order Book

no code implementations14 Jul 2019 Ke Xu, Martin D. Gould, Sam D. Howison

We study the multi-level order-flow imbalance (MLOFI), which is a vector quantity that measures the net flow of buy and sell orders at different price levels in a limit order book (LOB).

BERT-based Lexical Substitution

1 code implementation ACL 2019 Wangchunshu Zhou, Tao Ge, Ke Xu, Furu Wei, Ming Zhou

Our approach first applies dropout to the target word{'}s embedding for partially masking the word, allowing BERT to take balanced consideration of the target word{'}s semantics and contexts for proposing substitute candidates, and then validates the candidates based on their substitution{'}s influence on the global contextualized representation of the sentence.

Globally Soft Filter Pruning For Efficient Convolutional Neural Networks

no code implementations ICLR 2019 Ke Xu, Xiao-Yun Wang, Qun Jia, Jianjing An, Dong Wang

Therefore, accumulating the saliency of the filter over the entire data set can provide more accurate guidance for pruning.

Incremental training of multi-generative adversarial networks

no code implementations ICLR 2019 Qi Tan, Pingzhong Tang, Ke Xu, Weiran Shen, Song Zuo

Generative neural networks map a standard, possibly distribution to a complex high-dimensional distribution, which represents the real world data set.

Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset

2 code implementations CVPR 2019 Tianyu Wang, Xin Yang, Ke Xu, Shaozhe Chen, Qiang Zhang, Rynson Lau

Second, to better cover the stochastic distribution of real rain streaks, we propose a novel SPatial Attentive Network (SPANet) to remove rain streaks in a local-to-global manner.

Single Image Deraining Vocal Bursts Intensity Prediction

Active Matting

no code implementations NeurIPS 2018 Xin Yang, Ke Xu, Shaozhe Chen, Shengfeng He, Baocai Yin Yin, Rynson Lau

Our aim is to discover the most informative sequence of regions for user input in order to produce a good alpha matte with minimum labeling efforts.

Image Matting

Revisiting Image-Language Networks for Open-ended Phrase Detection

3 code implementations17 Nov 2018 Bryan A. Plummer, Kevin J. Shih, Yichen Li, Ke Xu, Svetlana Lazebnik, Stan Sclaroff, Kate Saenko

Most existing work that grounds natural language phrases in images starts with the assumption that the phrase in question is relevant to the image.

object-detection Object Detection +2

Diversified Top-k Partial MaxSAT Solving

no code implementations31 May 2017 Junping Zhou, Huanyao Sun, Feifei Ma, Jian Gao, Ke Xu, Minghao Yin

We introduce a diversified top-k partial MaxSAT problem, a combination of partial MaxSAT problem and enumeration problem.

Community Detection

Learning to Generate Product Reviews from Attributes

no code implementations EACL 2017 Li Dong, Shaohan Huang, Furu Wei, Mirella Lapata, Ming Zhou, Ke Xu

This paper presents an attention-enhanced attribute-to-sequence model to generate product reviews for given attribute information, such as user, product, and rating.

Review Generation Sentiment Analysis +1

Learning Influence Functions from Incomplete Observations

no code implementations NeurIPS 2016 Xinran He, Ke Xu, David Kempe, Yan Liu

We establish both proper and improper PAC learnability of influence functions under randomly missing observations.

Word Network Topic Model: A Simple but General Solution for Short and Imbalanced Texts

no code implementations17 Dec 2014 Yuan Zuo, Jichang Zhao, Ke Xu

The short text has been the prevalent format for information of Internet in recent decades, especially with the development of online social media, whose millions of users generate a vast number of short messages everyday.

Topic Models

A Statistical Parsing Framework for Sentiment Classification

no code implementations CL 2015 Li Dong, Furu Wei, Shujie Liu, Ming Zhou, Ke Xu

Unlike previous works that employ syntactic parsing results for sentiment analysis, we develop a statistical parser to directly analyze the sentiment structure of a sentence.

Classification General Classification +2

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