
BNinvariant sharpness regularizes the training model to better generalization
It is arguably believed that flatter minima can generalize better. Howev...
read it

Towards Accelerating Training of Batch Normalization: A Manifold Perspective
Batch normalization (BN) has become a crucial component across diverse d...
read it

Deep Generative Model for Efficient 3D Airfoil Parameterization and Generation
In aerodynamic shape optimization, the convergence and computational cos...
read it

FDMT: A Benchmark Dataset for Finegrained Domain Adaptation in Machine Translation
Previous domain adaptation research usually neglect the diversity in tra...
read it

Time Series Domain Adaptation via Sparse Associative Structure Alignment
Domain adaptation on time series data is an important but challenging ta...
read it

Nonstationarity Analysis of Materials Microstructures via Fisher Score Vectors
Microstructures are critical to the physical properties of materials. St...
read it

Identifying Invariant Texture Violation for Robust Deepfake Detection
Existing deepfake detection methods have reported promising indistribut...
read it

The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks
Despite their overwhelming capacity to overfit, deep neural networks tra...
read it

Multitask machine learning of collective variables for enhanced sampling of rare events
Computing accurate reaction rates is a central challenge in computationa...
read it

Maximizing Social Welfare in a Competitive Diffusion Model
Influence maximization (IM) has garnered a lot of attention in the liter...
read it

Wireless Image Transmission Using Deep Source Channel Coding With Attention Modules
Recent research on joint source channel coding (JSCC) for wireless commu...
read it

SHOTVAE: Semisupervised Deep Generative Models With Labelaware ELBO Approximations
Semisupervised variational autoencoders (VAEs) have obtained strong res...
read it

KD3A: Unsupervised MultiSource Decentralized Domain Adaptation via Knowledge Distillation
Conventional unsupervised multisource domain adaptation(UMDA) methods a...
read it

Compressive Sensing Based Joint Activity and Data Detection for GrantFree Massive Access
Massive machinetype communications (mMTC) are poised to provide ubiquit...
read it

Online Influence Maximization under Linear Threshold Model
Online influence maximization (OIM) is a popular problem in social netwo...
read it

Federated Learning via Intelligent Reflecting Surface
Overtheair computation (AirComp) based federated learning (FL) is capa...
read it

Enhanced Fewshot Learning for Intrusion Detection in Railway Video Surveillance
Video surveillance is gaining increasing popularity to assist in railway...
read it

Latent Causal Invariant Model
Current supervised learning can learn spurious correlation during the da...
read it

Learning Causal Semantic Representation for OutofDistribution Prediction
Conventional supervised learning methods, especially deep ones, are foun...
read it

Fast Convergence Algorithm for Analog Federated Learning
In this paper, we consider federated learning (FL) over a noisy fading m...
read it

New Ideas and Trends in Deep Multimodal Content Understanding: A Review
The focus of this survey is on the analysis of two modalities of multimo...
read it

On the Exploration of Incremental Learning for Finegrained Image Retrieval
In this paper, we consider the problem of finegrained image retrieval i...
read it

Hyperspectral Unmixing via Nonnegative Matrix Factorization with Handcrafted and Learnt Priors
Nowadays, nonnegative matrix factorization (NMF) based methods have been...
read it

Tempura: A General Cost Based Optimizer Framework for Incremental Data Processing (Extended Version)
Incremental processing is widelyadopted in many applications, ranging f...
read it

Fully Automatic Intervertebral Disc Segmentation Using Multimodal 3D UNet
Intervertebral discs (IVDs), as small joints lying between adjacent vert...
read it

ChoreoNet: Towards Music to Dance Synthesis with Choreographic Action Unit
Dance and music are two highly correlated artistic forms. Synthesizing d...
read it

Reconfigurable Intelligent Surface Assisted Massive MIMO with Antenna Selection
Antenna selection is capable of reducing the hardware complexity of mass...
read it

MOPaDGAN: Reparameterizing Engineering Designs for Augmented Multiobjective Optimization
Multiobjective optimization is key to solving many Engineering Design p...
read it

Structured Sparsity Modeling for Improved Multivariate Statistical Analysis based Fault Isolation
In order to improve the fault diagnosis capability of multivariate stati...
read it

PassVizor: Toward Better Understanding of the Dynamics of Soccer Passes
In soccer, passing is the most frequent interaction between players and ...
read it

Bubble Storytelling with Automated Animation: A Brexit Hashtag Activism Case Study
Hashtag data are common and easy to acquire. Thus, they are widely used ...
read it

GraphFederator: Federated Visual Analysis for Multiparty Graphs
This paper presents GraphFederator, a novel approach to construct joint ...
read it

New Directions in Distributed Deep Learning: Bringing the Network at Forefront of IoT Design
In this paper, we first highlight three major challenges to largescale ...
read it

Global Context Aware Convolutions for 3D Point Cloud Understanding
Recent advances in deep learning for 3D point clouds have shown great pr...
read it

Dual Gaussianbased Variational Subspace Disentanglement for VisibleInfrared Person ReIdentification
Visibleinfrared person reidentification (VIReID) is a challenging and...
read it

Exemplarbased Layout Finetuning for Nodelink Diagrams
We design and evaluate a novel layout finetuning technique for nodelin...
read it

SMAP: A Joint Dimensionality Reduction Scheme for Secure MultiParty Visualization
Nowadays, as data becomes increasingly complex and distributed, data ana...
read it

Revisiting the Modifiable Areal Unit Problem in Deep Traffic Prediction with Visual Analytics
Deep learning methods are being increasingly used for urban traffic pred...
read it

ConceptExplorer: Visual Analysis of Concept Driftsin Multisource Timeseries Data
Timeseries data is widely studied in various scenarios, like weather fo...
read it

Federated Visualization: A Privacypreserving Strategy for Decentralized Visualization
We present a novel privacy preservation strategy for decentralized visua...
read it

Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
The linear inverse problem is fundamental to the development of various ...
read it

Membership Inference with Privately Augmented Data Endorses the Benign while Suppresses the Adversary
Membership inference (MI) in machine learning decides whether a given ex...
read it

MOPaDGAN: Generating Diverse Designs with Multivariate Performance Enhancement
Deep generative models have proven useful for automatic design synthesis...
read it

Optimization from Structured Samples for Coverage Functions
We revisit the optimization from samples (OPS) model, which studies the ...
read it

Signal Encryption Strategy based on Domain change of the Fractional Fourier Transform
We provide a double encryption algorithm that uses the lack of invertibi...
read it

A LearningDriven Framework with Spatial Optimization For Surgical Suture Thread Reconstruction and Autonomous Grasping Under Multiple Topologies and Environmental Noises
Surgical knot tying is one of the most fundamental and important procedu...
read it

Molecular Latent Space Simulators
Small integration time steps limit molecular dynamics (MD) simulations t...
read it

Constructing Basis Path Set by Eliminating Path Dependency
The way the basis path set works in neural network remains mysterious, a...
read it

Deep Generative Modeling for Mechanisticbased Learning and Design of Metamaterial Systems
Metamaterials are emerging as a new paradigmatic material system to rend...
read it

DataDriven Topology Optimization with Multiclass Microstructures using Latent Variable Gaussian Process
The datadriven approach is emerging as a promising method for the topol...
read it
Wei Chen
is this you? claim profile
Senior Researcher at Microsoft Research Asia, Adjunct Professor in the Institute of Interdisciplinary Information Sciences, Tsinghua University, Adjunct Researcher in the Institute of Computing Technology, Chinese Academy of Sciences, Ph.D degree from the Department of Computer Science, Cornell University, Scientist at Oracle Corporation 2004.