
AlphaMatch: Improving Consistency for Semisupervised Learning with Alphadivergence
Semisupervised learning (SSL) is a key approach toward more dataeffici...
read it

KeepAugment: A Simple InformationPreserving Data Augmentation Approach
Data augmentation (DA) is an essential technique for training stateoft...
read it

Smart obervation method with wide field small aperture telescopes for real time transient detection
Wide field small aperture telescopes (WFSATs) are commonly used for fast...
read it

Modelling the Point Spread Function of Wide Field Small Aperture Telescopes With Deep Neural Networks – Applications in Point Spread Function Estimation
The point spread function (PSF) reflects states of a telescope and plays...
read it

Certified Monotonic Neural Networks
Learning monotonic models with respect to a subset of the inputs is a de...
read it

Debiasing Convolutional Neural Networks via Meta Orthogonalization
While deep learning models often achieve strong task performance, their ...
read it

Deep Active Graph Representation Learning
Graph neural networks (GNNs) aim to learn graph representations that pre...
read it

Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough
Despite the great success of deep learning, recent works show that large...
read it

OffPolicy Interval Estimation with Lipschitz Value Iteration
Offpolicy evaluation provides an essential tool for evaluating the effe...
read it

Graph Contrastive Learning with Adaptive Augmentation
Recently, contrastive learning (CL) has emerged as a successful method f...
read it

Population Gradients improve performance across datasets and architectures in object classification
The most successful methods such as ReLU transfer functions, batch norma...
read it

Adaptive DensetoSparse Paradigm for Pruning Online Recommendation System with NonStationary Data
Large scale deep learning provides a tremendous opportunity to improve t...
read it

An efficient representation of chronological events in medical texts
In this work we addressed the problem of capturing sequential informatio...
read it

Modeling Dyadic Conversations for Personality Inference
Nowadays, automatical personality inference is drawing extensive attenti...
read it

DNN2LR: Interpretationinspired Feature Crossing for Realworld Tabular Data
For sake of reliability, it is necessary for models in realworld applic...
read it

DeepSlicing: Deep Reinforcement Learning Assisted Resource Allocation for Network Slicing
Network slicing enables multiple virtual networks run on the same physic...
read it

Disentangled Item Representation for Recommender Systems
Item representations in recommendation systems are expected to reveal th...
read it

Accountable OffPolicy Evaluation With Kernel Bellman Statistics
We consider offpolicy evaluation (OPE), which evaluates the performance...
read it

Deep Active Learning by Model Interpretability
Recent successes of Deep Neural Networks (DNNs) in a variety of research...
read it

Edgeworth corrections for spot volatility estimator
We develop Edgeworth expansion theory for spot volatility estimator unde...
read it

Simplification of Graph Convolutional Networks: A Matrix Factorizationbased Perspective
In recent years, substantial progress has been made on Graph Convolution...
read it

TFNet: MultiSemantic Feature Interaction for CTR Prediction
The CTR (ClickThrough Rate) prediction plays a central role in the doma...
read it

Deep Graph Contrastive Representation Learning
Graph representation learning nowadays becomes fundamental in analyzing ...
read it

SAFER: A Structurefree Approach for Certified Robustness to Adversarial Word Substitutions
Stateoftheart NLP models can often be fooled by humanunaware transfo...
read it

TAGNN: Target Attentive Graph Neural Networks for Sessionbased Recommendation
Sessionbased recommendation nowadays plays a vital role in many website...
read it

An Empirical Study on Feature Discretization
When dealing with continuous numeric features, we usually adopt feature ...
read it

EdgeSlice: Slicing Wireless Edge Computing Network with Decentralized Deep Reinforcement Learning
5G and edge computing will serve various emerging use cases that have di...
read it

Dimension Independent Generalization Error with Regularized Online Optimization
One classical canon of statistics is that large models are prone to over...
read it

Blackbox Offpolicy Estimation for InfiniteHorizon Reinforcement Learning
Offpolicy estimation for longhorizon problems is important in many rea...
read it

Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting
We propose signed splitting steepest descent (S3D), which progressively ...
read it

Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection
Recent empirical works show that large deep neural networks are often hi...
read it

Med7: a transferable clinical natural language processing model for electronic health records
The field of clinical natural language processing has been advanced sign...
read it

Stein Variational Inference for Discrete Distributions
Gradientbased approximate inference methods, such as Stein variational ...
read it

Statistical Adaptive Stochastic Gradient Methods
We propose a statistical adaptive procedure called SALSA for automatical...
read it

Detection and Classification of Astronomical Targets with Deep Neural Networks in Wide Field Small Aperture Telescopes
Wide field small aperture telescopes are widely used in optical transien...
read it

BlackBox Certification with Randomized Smoothing: A Functional Optimization Based Framework
Randomized classifiers have been shown to provide a promising approach f...
read it

Stein SelfRepulsive Dynamics: Benefits From Past Samples
We propose a new Stein selfrepulsive dynamics for obtaining diversified...
read it

Posttraining Quantization with Multiple Points: Mixed Precision without Mixed Precision
We consider the posttraining quantization problem, which discretizes th...
read it

MaxUp: A Simple Way to Improve Generalization of Neural Network Training
We propose MaxUp, an embarrassingly simple, highly effective technique f...
read it

Attributed MultiRelational Attention Network for Factchecking URL Recommendation
To combat fake news, researchers mostly focused on detecting fake news a...
read it

Implicit Regularization of Normalization Methods
Normalization methods such as batch normalization are commonly used in o...
read it

Learning Preferences and Demands in Visual Recommendation
Visual information is an important factor in recommender systems, in whi...
read it

LearningAssisted Secure EndtoEnd Network Slicing for CyberPhysical Systems
There is a pressing need to interconnect physical systems such as power ...
read it

Stein Variational Gradient Descent With MatrixValued Kernels
Stein variational gradient descent (SVGD) is a particlebased inference ...
read it

A General Framework for Empirical Bayes Estimation in Discrete Linear Exponential Family
We develop a Nonparametric Empirical Bayes (NEB) framework for compound ...
read it

Doubly Robust Bias Reduction in Infinite Horizon OffPolicy Estimation
Infinite horizon offpolicy policy evaluation is a highly challenging ta...
read it

EnergyAware Neural Architecture Optimization with Fast Splitting Steepest Descent
Designing energyefficient networks is of critical importance for enabli...
read it

Splitting Steepest Descent for Growing Neural Architectures
We develop a progressive training approach for neural networks which ada...
read it

Training Robust Deep Neural Networks via Adversarial Noise Propagation
Deep neural networks have been found vulnerable to noises like adversari...
read it

Polar Codes with Memory
Polar codes with memory (PCM) are proposed in this paper: a pair of cons...
read it
Qiang Liu
verfied profile
Assistant Professor at Department of Computer Science, The University of Texas at Austin