
Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution
Recent studies show that neural natural language processing (NLP) models...
read it

Efficient Estimation For The Joint Model of Survival and Longitudinal Data
In survival studies it is important to record the values of key longitud...
read it

ImagetoVideo Generation via 3D Facial Dynamics
We present a versatile model, FaceAnime, for various video generation ta...
read it

Controlling the False Discovery Rate in Structural Sparsity: Split Knockoffs
Controlling the False Discovery Rate (FDR) in a variable selection proce...
read it

Visual Distant Supervision for Scene Graph Generation
Scene graph generation aims to identify objects and their relations in i...
read it

UPRec: UserAware Pretraining for Recommender Systems
Existing sequential recommendation methods rely on large amounts of trai...
read it

On Stochastic Variance Reduced Gradient Method for Semidefinite Optimization
The lowrank stochastic semidefinite optimization has attracted rising a...
read it

StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding
The generation of stylish Chinese fonts is an important problem involved...
read it

An exact solution in Markov decision process with multiplicative rewards as a general framework
We develop an exactly solvable framework of Markov decision process with...
read it

Denoising Relation Extraction from Documentlevel Distant Supervision
Distant supervision (DS) has been widely used to generate autolabeled d...
read it

Knowledge Transfer via Pretraining for Recommendation: A Review and Prospect
Recommender systems aim to provide item recommendations for users, and a...
read it

Robust Autoencoder GAN for CryoEM Image Denoising
The cryoelectron microscopy (CryoEM) becomes popular for macromolecula...
read it

Multisource Heterogeneous Domain Adaptation with Conditional Weighting Adversarial Network
Heterogeneous domain adaptation (HDA) tackles the learning of crossdoma...
read it

Leveraging both Lesion Features and Procedural Bias in Neuroimaging: An DualTask Split dynamics of inverse scale space
The prediction and selection of lesion features are two important tasks ...
read it

How to trust unlabeled data? Instance Credibility Inference for FewShot Learning
Deep learning based models have excelled in many computer vision task an...
read it

DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths
Overparameterization is ubiquitous nowadays in training neural networks...
read it

Crossmodal Language Grounding in an Embodied Neurocognitive Model
Human infants are able to acquire natural language seemingly easily at a...
read it

Video Playback Rate Perception for SelfsupervisedSpatioTemporal Representation Learning
In selfsupervised spatiotemporal representation learning, the temporal...
read it

Exploring Private Federated Learning with Laplacian Smoothing
Federated learning aims to protect data privacy by collaboratively learn...
read it

Boosting Semantic Human Matting with Coarse Annotations
Semantic human matting aims to estimate the perpixel opacity of the for...
read it

Learning the mapping x∑_i=1^d x_i^2: the cost of finding the needle in a haystack
The task of using machine learning to approximate the mapping x∑_i=1^d x...
read it

Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction
Reconstruction of a 3D shape from a single 2D image is a classical compu...
read it

SMAUG: EndtoEnd FullStack Simulation Infrastructure for Deep Learning Workloads
In recent years, there has been tremendous advances in hardware accelera...
read it

Fast Stochastic Ordinal Embedding with Variance Reduction and Adaptive Step Size
Learning representation from relative similarity comparisons, often call...
read it

Adversarial Language Games for Advanced Natural Language Intelligence
While adversarial games have been well studied in various board games an...
read it

iSplit LBI: Individualized Partial Ranking with Ties via Split LBI
Due to the inherent uncertainty of data, the problem of predicting parti...
read it

Characterizing Membership Privacy in Stochastic Gradient Langevin Dynamics
Bayesian deep learning is recently regarded as an intrinsic way to chara...
read it

OpenNRE: An Open and Extensible Toolkit for Neural Relation Extraction
OpenNRE is an opensource and extensible toolkit that provides a unified...
read it

An Acceleration Framework for High Resolution Image Synthesis
Synthesis of high resolution images using Generative Adversarial Network...
read it

Heterogeneous Domain Adaptation via Soft Transfer Network
Heterogeneous domain adaptation (HDA) aims to facilitate the learning ta...
read it

DocRED: A LargeScale DocumentLevel Relation Extraction Dataset
Multiple entities in a document generally exhibit complex intersentence...
read it

Parsimonious Deep Learning: A Differential Inclusion Approach with Global Convergence
Overparameterization is ubiquitous nowadays in training neural networks...
read it

Efficient Estimation For The Cox Proportional Hazards Cure Model
While analysing timetoevent data, it is possible that a certain fracti...
read it

S^2LBI: Stochastic Split Linearized Bregman Iterations for Parsimonious Deep Learning
This paper proposes a novel Stochastic Split Linearized Bregman Iteratio...
read it

Deep Robust Subjective Visual Property Prediction in Crowdsourcing
The problem of estimating subjective visual properties (SVP) of images (...
read it

Generative Adversarial Nets for Robust Scatter Estimation: A Proper Scoring Rule Perspective
Robust scatter estimation is a fundamental task in statistics. The recen...
read it

BOLTSSI: A Statistical Approach to Screening Interaction Effects for UltraHigh Dimensional Data
Detecting interaction effects is a crucial step in various applications....
read it

A Convergence Analysis of Nonlinearly Constrained ADMM in Deep Learning
Efficient training of deep neural networks (DNNs) is a challenge due to ...
read it

Attentionaware Multistroke Style Transfer
Neural style transfer has drawn considerable attention from both academi...
read it

Multiview Crosssupervision for Semantic Segmentation
This paper presents a semisupervised learning framework for a customize...
read it

FewRel: A LargeScale Supervised FewShot Relation Classification Dataset with StateoftheArt Evaluation
We present a FewShot Relation Classification Dataset (FewRel), consisti...
read it

DataDriven Tight Frame for CryoEM Image Denoising and Conformational Classification
The cryoelectron microscope (cryoEM) is increasingly popular these yea...
read it

A Unified Dynamic Approach to Sparse Model Selection
Sparse model selection is ubiquitous from linear regression to graphical...
read it

On Breiman's Dilemma in Neural Networks: Phase Transitions of Margin Dynamics
Margin enlargement over training data has been an important strategy sin...
read it

Robust Estimation and Generative Adversarial Nets
Robust estimation under Huber's ϵcontamination model has become an impo...
read it

A Marginbased MLE for Crowdsourced Partial Ranking
A preference order or ranking aggregated from pairwise comparison data i...
read it

FDRHS: An Empirical Bayesian Identification of Heterogenous Features in Neuroimage Analysis
Recent studies found that in voxelbased neuroimage analysis, detecting ...
read it

MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Fewshot and Zeroshot Learning
It is one typical and general topic of learning a good embedding model t...
read it

MONET: Multiview Semisupervised Keypoint via Epipolar Divergence
This paper presents MONETan endtoend semisupervised learning frame...
read it

A Proximal Block Coordinate Descent Algorithm for Deep Neural Network Training
Training deep neural networks (DNNs) efficiently is a challenge due to t...
read it
Yuan Yao
is this you? claim profile
Associate Professor at The Hong Kong University of Science and Technology