Search Results for author: Wei Huang

Found 67 papers, 28 papers with code

Exploring Label Hierarchy in a Generative Way for Hierarchical Text Classification

no code implementations COLING 2022 Wei Huang, Chen Liu, Bo Xiao, Yihua Zhao, Zhaoming Pan, Zhimin Zhang, Xinyun Yang, Guiquan Liu

Hierarchical Text Classification (HTC), which aims to predict text labels organized in hierarchical space, is a significant task lacking in investigation in natural language processing.

text-classification Text Classification

Generic-to-Specific Distillation of Masked Autoencoders

1 code implementation28 Feb 2023 Wei Huang, Zhiliang Peng, Li Dong, Furu Wei, Jianbin Jiao, Qixiang Ye

Lightweight ViT models limited by the model capacity, however, benefit little from those pre-training mechanisms.

Image Classification Knowledge Distillation +3

Communication under Mixed Gaussian-Impulsive Channel: An End-to-End Framework

no code implementations19 Jan 2023 Chengjie Zhao, Jun Wang, Wei Huang, Xiaonan Chen, Tianfu Qi

Under MGIN channel, classical communication signal schemes and corresponding detection methods usually can not achieve desirable performance as they are optimized with respect to WGN.

TCFimt: Temporal Counterfactual Forecasting from Individual Multiple Treatment Perspective

no code implementations17 Dec 2022 Pengfei Xi, Guifeng Wang, Zhipeng Hu, Yu Xiong, Mingming Gong, Wei Huang, Runze Wu, Yu Ding, Tangjie Lv, Changjie Fan, Xiangnan Feng

TCFimt constructs adversarial tasks in a seq2seq framework to alleviate selection and time-varying bias and designs a contrastive learning-based block to decouple a mixed treatment effect into separated main treatment effects and causal interactions which further improves estimation accuracy.

Contrastive Learning Decision Making +2

Can Single-Pass Contrastive Learning Work for Both Homophilic and Heterophilic Graph?

1 code implementation20 Nov 2022 Haonan Wang, Jieyu Zhang, Qi Zhu, Wei Huang

To answer this, we analyze the concentration property of features obtained by neighborhood aggregation on both homophilic and heterophilic graphs, introduce the single-pass graph contrastive learning loss based on the property, and provide performance guarantees of the minimizer of the loss on downstream tasks.

Contrastive Learning

ViT-LSLA: Vision Transformer with Light Self-Limited-Attention

no code implementations31 Oct 2022 Zhenzhe Hechen, Wei Huang, Yixin Zhao

Consequently, this paper presents a light self-limited-attention (LSLA) consisting of a light self-attention mechanism (LSA) to save the computation cost and the number of parameters, and a self-limited-attention mechanism (SLA) to improve the performance.

Variance reduced Shapley value estimation for trustworthy data valuation

no code implementations30 Oct 2022 Mengmeng Wu, Ruoxi Jia, Changle lin, Wei Huang, Xiangyu Chang

Data valuation, especially quantifying data value in algorithmic prediction and decision-making, is a fundamental problem in data trading scenarios.

Data Valuation Decision Making

Anisotropic multiresolution analyses for deepfake detection

no code implementations26 Oct 2022 Wei Huang, Michelangelo Valsecchi, Michael Multerer

We employ the fully separable wavelet transform and multiwavelets to obtain the anisotropic features to feed to standard CNN classifiers.

DeepFake Detection Face Swapping

Joint Microstrip Selection and Beamforming Design for MmWave Systems with Dynamic Metasurface Antennas

no code implementations22 Oct 2022 Wei Huang, Haiyang Zhang, Nir Shlezinger, Yonina C. Eldar

Dynamic metasurface antennas (DMAs) provide a new paradigm to realize large-scale antenna arrays for future wireless systems.

Identifiability and Asymptotics in Learning Homogeneous Linear ODE Systems from Discrete Observations

no code implementations12 Oct 2022 Yuanyuan Wang, Wei Huang, Mingming Gong, Xi Geng, Tongliang Liu, Kun Zhang, DaCheng Tao

This paper derives a sufficient condition for the identifiability of homogeneous linear ODE systems from a sequence of equally-spaced error-free observations sampled from a single trajectory.

Solving combinational optimization problems with evolutionary single-pixel imaging

no code implementations12 Oct 2022 Wei Huang, Jiaxiang Li, Shuming Jiao, Zibang Zhang

Single-pixel imaging (SPI) is a novel optical imaging technique by replacing the pixelated sensor array in a conventional camera with a single-pixel detector.

VLSNR:Vision-Linguistics Coordination Time Sequence-aware News Recommendation

1 code implementation6 Oct 2022 Songhao Han, Wei Huang, Xiaotian Luan

In our work, we propose a vision-linguistics coordinate time sequence news recommendation.

News Recommendation

On the Sparse DAG Structure Learning Based on Adaptive Lasso

no code implementations7 Sep 2022 Danru Xu, Erdun Gao, Wei Huang, Menghan Wang, Andy Song, Mingming Gong

Learning the underlying Bayesian Networks (BNs), represented by directed acyclic graphs (DAGs), of the concerned events from purely-observational data is a crucial part of evidential reasoning.

Parameter Estimation of Mixed Gaussian-Impulsive Noise: An U-net++ Based Method

no code implementations6 Sep 2022 Tianfu Qi, Jun Wang, Xiaonan Chen, Wei Huang

In many scenarios, the communication system suffers from both Gaussian white noise and non-Gaussian impulsive noise.

SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability

1 code implementation19 Aug 2022 Wei Huang, Xingyu Zhao, Gaojie Jin, Xiaowei Huang

Interpretability of Deep Learning (DL) models is arguably the barrier in front of trustworthy AI.

HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling

no code implementations30 May 2022 Xiaosong Zhang, Yunjie Tian, Wei Huang, Qixiang Ye, Qi Dai, Lingxi Xie, Qi Tian

A key idea of efficient implementation is to discard the masked image patches (or tokens) throughout the target network (encoder), which requires the encoder to be a plain vision transformer (e. g., ViT), albeit hierarchical vision transformers (e. g., Swin Transformer) have potentially better properties in formulating vision inputs.

Transfer Learning

MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models

1 code implementation27 May 2022 Erdun Gao, Ignavier Ng, Mingming Gong, Li Shen, Wei Huang, Tongliang Liu, Kun Zhang, Howard Bondell

In this paper, we develop a general method, which we call MissDAG, to perform causal discovery from data with incomplete observations.

Causal Discovery Imputation +1

Hierarchical Distribution-Aware Testing of Deep Learning

1 code implementation17 May 2022 Wei Huang, Xingyu Zhao, Alec Banks, Victoria Cox, Xiaowei Huang

In this paper, we propose a new robustness testing approach for detecting AEs that considers both the input distribution and the perceptual quality of inputs.

Data Compression

Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis

2 code implementations11 May 2022 Wuyang Chen, Wei Huang, Xinyu Gong, Boris Hanin, Zhangyang Wang

Advanced deep neural networks (DNNs), designed by either human or AutoML algorithms, are growing increasingly complex.

Neural Architecture Search

Playing Tic-Tac-Toe Games with Intelligent Single-pixel Imaging

no code implementations7 May 2022 Shuming Jiao, Jiaxiang Li, Wei Huang, Zibang Zhang

Single-pixel imaging (SPI) is a novel optical imaging technique by replacing a two-dimensional pixelated sensor with a single-pixel detector and pattern illuminations.

Augmentation-Free Graph Contrastive Learning with Performance Guarantee

no code implementations11 Apr 2022 Haonan Wang, Jieyu Zhang, Qi Zhu, Wei Huang

Graph contrastive learning (GCL) is the most representative and prevalent self-supervised learning approach for graph-structured data.

Contrastive Learning Self-Supervised Learning

Enhancing Adversarial Training with Second-Order Statistics of Weights

1 code implementation CVPR 2022 Gaojie Jin, Xinping Yi, Wei Huang, Sven Schewe, Xiaowei Huang

In this paper, we show that treating model weights as random variables allows for enhancing adversarial training through \textbf{S}econd-Order \textbf{S}tatistics \textbf{O}ptimization (S$^2$O) with respect to the weights.

An Audio-Visual Attention Based Multimodal Network for Fake Talking Face Videos Detection

no code implementations10 Mar 2022 Ganglai Wang, Peng Zhang, Lei Xie, Wei Huang, Yufei zha, Yanning Zhang

DeepFake based digital facial forgery is threatening the public media security, especially when lip manipulation has been used in talking face generation, the difficulty of fake video detection is further improved.

Decision Making Face Detection +2

Attention-Based Lip Audio-Visual Synthesis for Talking Face Generation in the Wild

no code implementations8 Mar 2022 Ganglai Wang, Peng Zhang, Lei Xie, Wei Huang, Yufei zha

Rather than focusing on the unimportant regions of the face image, the proposed AttnWav2Lip model is able to pay more attention on the lip region reconstruction.

Talking Face Generation

Audio-visual speech separation based on joint feature representation with cross-modal attention

no code implementations5 Mar 2022 Junwen Xiong, Peng Zhang, Lei Xie, Wei Huang, Yufei zha, Yanning Zhang

Multi-modal based speech separation has exhibited a specific advantage on isolating the target character in multi-talker noisy environments.

Optical Flow Estimation Speech Separation

Look\&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement

1 code implementation4 Mar 2022 Junwen Xiong, Yu Zhou, Peng Zhang, Lei Xie, Wei Huang, Yufei zha

Active speaker detection and speech enhancement have become two increasingly attractive topics in audio-visual scenario understanding.

Multi-Task Learning Speech Enhancement

Auto-scaling Vision Transformers without Training

1 code implementation ICLR 2022 Wuyang Chen, Wei Huang, Xianzhi Du, Xiaodan Song, Zhangyang Wang, Denny Zhou

The motivation comes from two pain spots: 1) the lack of efficient and principled methods for designing and scaling ViTs; 2) the tremendous computational cost of training ViT that is much heavier than its convolution counterpart.

Demystify Optimization and Generalization of Over-parameterized PAC-Bayesian Learning

no code implementations4 Feb 2022 Wei Huang, Chunrui Liu, Yilan Chen, Tianyu Liu, Richard Yi Da Xu

In addition to being a pure generalization bound analysis tool, PAC-Bayesian bound can also be incorporated into an objective function to train a probabilistic neural network, making them a powerful and relevant framework that can numerically provide a tight generalization bound for supervised learning.

Achieving Efficient Distributed Machine Learning Using a Novel Non-Linear Class of Aggregation Functions

no code implementations29 Jan 2022 Haizhou Du, Ryan Yang, Yijian Chen, Qiao Xiang, Andre Wibisono, Wei Huang

In this paper, we analyze properties of the WPM and rigorously prove convergence properties of our aggregation mechanism.

Autonomous Driving

Knowledge Graph Based Waveform Recommendation: A New Communication Waveform Design Paradigm

no code implementations24 Jan 2022 Wei Huang, Tianfu Qi, Yundi Guan, Qihang Peng, Jun Wang

In this paper, we investigate the waveform design from a novel perspective and propose a new waveform design paradigm with the knowledge graph (KG)-based intelligent recommendation system.

Collaborative Filtering Intelligent Communication +1

Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurance

no code implementations30 Nov 2021 Yi Dong, Wei Huang, Vibhav Bharti, Victoria Cox, Alec Banks, Sen Wang, Xingyu Zhao, Sven Schewe, Xiaowei Huang

The increasing use of Machine Learning (ML) components embedded in autonomous systems -- so-called Learning-Enabled Systems (LESs) -- has resulted in the pressing need to assure their functional safety.

Semantic-Aware Generation for Self-Supervised Visual Representation Learning

1 code implementation25 Nov 2021 Yunjie Tian, Lingxi Xie, Xiaopeng Zhang, Jiemin Fang, Haohang Xu, Wei Huang, Jianbin Jiao, Qi Tian, Qixiang Ye

In this paper, we propose a self-supervised visual representation learning approach which involves both generative and discriminative proxies, where we focus on the former part by requiring the target network to recover the original image based on the mid-level features.

Representation Learning Semantic Segmentation

On the Equivalence between Neural Network and Support Vector Machine

1 code implementation NeurIPS 2021 Yilan Chen, Wei Huang, Lam M. Nguyen, Tsui-Wei Weng

Therefore, in this work, we propose to establish the equivalence between NN and SVM, and specifically, the infinitely wide NN trained by soft margin loss and the standard soft margin SVM with NTK trained by subgradient descent.


Deep Active Learning by Leveraging Training Dynamics

no code implementations16 Oct 2021 Haonan Wang, Wei Huang, Ziwei Wu, Andrew Margenot, Hanghang Tong, Jingrui He

Active learning theories and methods have been extensively studied in classical statistical learning settings.

Active Learning

Long-tailed Distribution Adaptation

1 code implementation6 Oct 2021 Zhiliang Peng, Wei Huang, Zonghao Guo, Xiaosong Zhang, Jianbin Jiao, Qixiang Ye

We propose to jointly optimize empirical risks of the unbalanced and balanced domains and approximate their domain divergence by intra-class and inter-class distances, with the aim to adapt models trained on the long-tailed distribution to general distributions in an interpretable way.

Domain Adaptation Instance Segmentation +3

Hierarchy-Aware T5 with Path-Adaptive Mask Mechanism for Hierarchical Text Classification

no code implementations17 Sep 2021 Wei Huang, Chen Liu, Yihua Zhao, Xinyun Yang, Zhaoming Pan, Zhimin Zhang, Guiquan Liu

Hierarchical Text Classification (HTC), which aims to predict text labels organized in hierarchical space, is a significant task lacking in investigation in natural language processing.

text-classification Text Classification

Unsupervised Cross-Modal Distillation for Thermal Infrared Tracking

1 code implementation31 Jul 2021 Jingxian Sun, Lichao Zhang, Yufei zha, Abel Gonzalez-Garcia, Peng Zhang, Wei Huang, Yanning Zhang

To solve this problem, we propose to distill representations of the TIR modality from the RGB modality with Cross-Modal Distillation (CMD) on a large amount of unlabeled paired RGB-TIR data.

Transfer Learning

Heterogeneous network-based drug repurposing for COVID-19

1 code implementation20 Jul 2021 Shuting Jin, Xiangxiang Zeng, Wei Huang, Feng Xia, Changzhi Jiang, Xiangrong Liu, Shaoliang Peng

The Corona Virus Disease 2019 (COVID-19) belongs to human coronaviruses (HCoVs), which spreads rapidly around the world.

Differentiable Architecture Search Meets Network Pruning at Initialization: A More Reliable, Efficient, and Flexible Framework

no code implementations22 Jun 2021 Miao Zhang, Steven Su, Shirui Pan, Xiaojun Chang, Wei Huang, Bin Yang, Gholamreza Haffari

Although Differentiable ARchiTecture Search (DARTS) has become the mainstream paradigm in Neural Architecture Search (NAS) due to its simplicity and efficiency, more recent works found that the performance of the searched architecture barely increases with the optimization proceeding in DARTS, and the final magnitudes obtained by DARTS could hardly indicate the importance of operations.

Network Pruning Neural Architecture Search

Conformer: Local Features Coupling Global Representations for Visual Recognition

4 code implementations ICCV 2021 Zhiliang Peng, Wei Huang, Shanzhi Gu, Lingxi Xie, YaoWei Wang, Jianbin Jiao, Qixiang Ye

Within Convolutional Neural Network (CNN), the convolution operations are good at extracting local features but experience difficulty to capture global representations.

Image Classification Instance Segmentation +4

PD-GAN: Probabilistic Diverse GAN for Image Inpainting

1 code implementation CVPR 2021 Hongyu Liu, Ziyu Wan, Wei Huang, Yibing Song, Xintong Han, Jing Liao

To this end, we propose spatially probabilistic diversity normalization (SPDNorm) inside the modulation to model the probability of generating a pixel conditioned on the context information.

Image Inpainting Image Restoration

Advanced Deep Networks for 3D Mitochondria Instance Segmentation

1 code implementation16 Apr 2021 Mingxing Li, Chang Chen, Xiaoyu Liu, Wei Huang, Yueyi Zhang, Zhiwei Xiong

Mitochondria instance segmentation from electron microscopy (EM) images has seen notable progress since the introduction of deep learning methods.

3D Instance Segmentation Denoising +1

Detecting Operational Adversarial Examples for Reliable Deep Learning

no code implementations13 Apr 2021 Xingyu Zhao, Wei Huang, Sven Schewe, Yi Dong, Xiaowei Huang

The utilisation of Deep Learning (DL) raises new challenges regarding its dependability in critical applications.

Towards Optimal Algorithms for Multi-Player Bandits without Collision Sensing Information

no code implementations24 Mar 2021 Wei Huang, Richard Combes, Cindy Trinh

We propose a novel algorithm for multi-player multi-armed bandits without collision sensing information.

Multi-Armed Bandits

DeFLOCNet: Deep Image Editing via Flexible Low-level Controls

1 code implementation CVPR 2021 Hongyu Liu, Ziyu Wan, Wei Huang, Yibing Song, Xintong Han, Jing Liao, Bing Jiang, Wei Liu

While existing methods combine an input image and these low-level controls for CNN inputs, the corresponding feature representations are not sufficient to convey user intentions, leading to unfaithfully generated content.

Texture Synthesis

Sequential Random Network for Fine-grained Image Classification

no code implementations12 Mar 2021 Chaorong Li, Malu Zhang, Wei Huang, Fengqing Qin, Anping Zeng, Yuanyuan Huang

To address this issue, we use the proposed SRN which composed of BiLSTM and several Tanh-Dropout blocks (called BiLSTM-TDN), to further process DCNN one-dimensional features for highlighting the detail information of image.


Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective

no code implementations ICLR 2022 Wei Huang, Yayong Li, Weitao Du, Jie Yin, Richard Yi Da Xu, Ling Chen, Miao Zhang

Inspired by our theoretical insights on trainability, we propose Critical DropEdge, a connectivity-aware and graph-adaptive sampling method, to alleviate the exponential decay problem more fundamentally.

A Unified Framework for Specification Tests of Continuous Treatment Effect Models

no code implementations16 Feb 2021 Wei Huang, Oliver Linton, Zheng Zhang

We propose a general framework for the specification testing of continuous treatment effect models.

Fairness and Accuracy in Federated Learning

no code implementations18 Dec 2020 Wei Huang, Tianrui Li, Dexian Wang, Shengdong Du, Junbo Zhang

An appropriate weight selection algorithm that combines the information quantity of training accuracy and training frequency to measure the weights is proposed.

Fairness Federated Learning

BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations

2 code implementations5 Dec 2020 Xingyu Zhao, Wei Huang, Xiaowei Huang, Valentin Robu, David Flynn

Given the pressing need for assuring algorithmic transparency, Explainable AI (XAI) has emerged as one of the key areas of AI research.

Implicit bias of deep linear networks in the large learning rate phase

no code implementations25 Nov 2020 Wei Huang, Weitao Du, Richard Yi Da Xu, Chunrui Liu

We claim that depending on the separation conditions of data, the gradient descent iterates will converge to a flatter minimum in the catapult phase.

Embedding and Extraction of Knowledge in Tree Ensemble Classifiers

2 code implementations16 Oct 2020 Wei Huang, Xingyu Zhao, Xiaowei Huang

Whilst, as the increasing use of machine learning models in security-critical applications, the embedding and extraction of malicious knowledge are equivalent to the notorious backdoor attack and its defence, respectively.

Backdoor Attack BIG-bench Machine Learning

Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations

1 code implementation ECCV 2020 Hongyu Liu, Bin Jiang, Yibing Song, Wei Huang, Chao Yang

We use CNN features from the deep and shallow layers of the encoder to represent structures and textures of an input image, respectively.

Image Inpainting

Achievable Rate Region of MISO Interference Channel Aided by Intelligent Reflecting Surface

no code implementations19 May 2020 Wei Huang, Yong Zeng, Yongming Huang

This paper investigates the achievable rate region of the multiple-input single-output (MISO) interference channel aided by intelligent reflecting surfaces (IRSs).

On the Neural Tangent Kernel of Deep Networks with Orthogonal Initialization

2 code implementations13 Apr 2020 Wei Huang, Weitao Du, Richard Yi Da Xu

The prevailing thinking is that orthogonal weights are crucial to enforcing dynamical isometry and speeding up training.

Gaussian Process Latent Variable Model Factorization for Context-aware Recommender Systems

2 code implementations19 Dec 2019 Wei Huang, Richard Yi Da Xu

Our work is primarily inspired by the Gaussian Process Latent Variable Model (GPLVM), which was a non-linear dimensionality reduction method.

Dimensionality Reduction Recommendation Systems

Mean field theory for deep dropout networks: digging up gradient backpropagation deeply

1 code implementation19 Dec 2019 Wei Huang, Richard Yi Da Xu, Weitao Du, Yutian Zeng, Yunce Zhao

In recent years, the mean field theory has been applied to the study of neural networks and has achieved a great deal of success.

One-Stage Inpainting with Bilateral Attention and Pyramid Filling Block

no code implementations18 Dec 2019 Hongyu Liu, Bin Jiang, Wei Huang, Chao Yang

However, the two-stage architecture is time-consuming, the contextual information lack high-level semantics and ignores both the semantic relevance and distance information of hole's feature patches, these limitations result in blurry textures and distorted structures of final result.

Image Inpainting Texture Synthesis

Coverage Guided Testing for Recurrent Neural Networks

1 code implementation5 Nov 2019 Wei Huang, Youcheng Sun, Xingyu Zhao, James Sharp, Wenjie Ruan, Jie Meng, Xiaowei Huang

The test metrics and test case generation algorithm are implemented into a tool TestRNN, which is then evaluated on a set of LSTM benchmarks.

Defect Detection Drug Discovery +3

Transferability of Spectral Graph Convolutional Neural Networks

no code implementations30 Jul 2019 Ron Levie, Wei Huang, Lorenzo Bucci, Michael M. Bronstein, Gitta Kutyniok

Transferability, which is a certain type of generalization capability, can be loosely defined as follows: if two graphs describe the same phenomenon, then a single filter or ConvNet should have similar repercussions on both graphs.

testRNN: Coverage-guided Testing on Recurrent Neural Networks

1 code implementation20 Jun 2019 Wei Huang, Youcheng Sun, Xiaowei Huang, James Sharp

Recurrent neural networks (RNNs) have been widely applied to various sequential tasks such as text processing, video recognition, and molecular property prediction.

Molecular Property Prediction Video Recognition

Attributes-aided Part Detection and Refinement for Person Re-identification

no code implementations27 Feb 2019 Shuzhao Li, Huimin Yu, Wei Huang, Jing Zhang

Person attributes are often exploited as mid-level human semantic information to help promote the performance of person re-identification task.

Person Re-Identification

Multiobjective Optimization Differential Evolution Enhanced with Principle Component Analysis for Constrained Optimization

no code implementations1 May 2018 Wei Huang, Tao Xu, Kangshun Li, Jun He

PMODE and HECO-PDE are compared with the algorithms from the IEEE CEC 2018 competition and another recent MOEA for constrained optimisation.

Multiobjective Optimization

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