105 citations · 372 across the 39 of their papers we have counts for
21 papers · 1 filter
A Convergent ADMM Framework for Efficient Neural Network Training
Junxiang Wang, Hongyi Li, Liang Zhao
As a well-known optimization framework, the Alternating Direction Method of Multipliers (ADMM) has achieved tremendous success in many classification and regression applications. R…
KNAS: Green Neural Architecture Search
Jingjing Xu, Liang Zhao, Junyang Lin +3
Many existing neural architecture search (NAS) solutions rely on downstream training for architecture evaluation, which takes enormous computations. Considering that these computat…
Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks
Zhiqian Chen, Fanglan Chen, Lei Zhang +7
Deep learning's performance has been extensively recognized recently. Graph neural networks (GNNs) are designed to deal with graph-structural data that classical deep learning does…
Schematic Memory Persistence and Transience for Efficient and Robust Continual Learning
Yuyang Gao, Giorgio A. Ascoli, Liang Zhao
Continual learning is considered a promising step towards next-generation Artificial Intelligence (AI), where deep neural networks (DNNs) make decisions by continuously learning a…
Sign-regularized Multi-task Learning
Johnny Torres, Guangji Bai, Junxiang Wang +3
Multi-task learning is a framework that enforces different learning tasks to share their knowledge to improve their generalization performance. It is a hot and active domain that s…
Disentangled Dynamic Graph Deep Generation
Wenbin Zhang, Liming Zhang, Dieter Pfoser +1
Deep generative models for graphs have exhibited promising performance in ever-increasing domains such as design of molecules (i.e, graph of atoms) and structure prediction of prot…
Tunable Subnetwork Splitting for Model-parallelism of Neural Network Training
Junxiang Wang, Zheng Chai, Yue Cheng +1
Alternating minimization methods have recently been proposed as alternatives to the gradient descent for deep neural network optimization. Alternating minimization methods can typi…
A Systematic Survey on Deep Generative Models for Graph Generation
Xiaojie Guo, Liang Zhao
Graphs are important data representations for describing objects and their relationships, which appear in a wide diversity of real-world scenarios. As one of a critical problem in…
TG-GAN: Continuous-time Temporal Graph Generation with Deep Generative Models
Liming Zhang, Liang Zhao, Shan Qin +1
The recent deep generative models for static graphs that are now being actively developed have achieved significant success in areas such as molecule design. However, many real-wor…
Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks
Zhiqian Chen, Fanglan Chen, Lei Zhang +7
Deep learning's success has been widely recognized in a variety of machine learning tasks, including image classification, audio recognition, and natural language processing. As an…
Interpreting and Evaluating Neural Network Robustness
Fuxun Yu, Zhuwei Qin, Chenchen Liu +3
Recently, adversarial deception becomes one of the most considerable threats to deep neural networks. However, compared to extensive research in new designs of various adversarial…
Learning Good Representation via Continuous Attention
Liang Zhao, Wei Xu
In this paper we present our scientific discovery that good representation can be learned via continuous attention during the interaction between Unsupervised Learning(UL) and Rein…
WALL-E: An Efficient Reinforcement Learning Research Framework
Tianbing Xu, Andrew Zhang, Liang Zhao
There are two halves to RL systems: experience collection time and policy learning time. For a large number of samples in rollouts, experience collection time is the major bottlene…
Interpreting Adversarial Robustness: A View from Decision Surface in Input Space
Fuxun Yu, Chenchen Liu, Yanzhi Wang +2
One popular hypothesis of neural network generalization is that the flat local minima of loss surface in parameter space leads to good generalization. However, we demonstrate that…
Functionality-Oriented Convolutional Filter Pruning
Zhuwei Qin, Fuxun Yu, Chenchen Liu +1
The sophisticated structure of Convolutional Neural Network (CNN) allows for outstanding performance, but at the cost of intensive computation. As significant redundancies inevitab…
Distributed Self-Paced Learning in Alternating Direction Method of Multipliers
Xuchao Zhang, Liang Zhao, Zhiqian Chen +1
Self-paced learning (SPL) mimics the cognitive process of humans, who generally learn from easy samples to hard ones. One key issue in SPL is the training process required for each…
Deep Graph Translation
Xiaojie Guo, Lingfei Wu, Liang Zhao
Inspired by the tremendous success of deep generative models on generating continuous data like image and audio, in the most recent year, few deep graph generative models have been…
Learning to Explore with Meta-Policy Gradient
Tianbing Xu, Qiang Liu, Liang Zhao +1
The performance of off-policy learning, including deep Q-learning and deep deterministic policy gradient (DDPG), critically depends on the choice of the exploration policy. Existin…
On the Universal Approximation Property and Equivalence of Stochastic Computing-based Neural Networks and Binary Neural Networks
Yanzhi Wang, Zheng Zhan, Jiayu Li +6
Large-scale deep neural networks are both memory intensive and computation-intensive, thereby posing stringent requirements on the computing platforms. Hardware accelerations of de…
Unsupervised Learning Layers for Video Analysis
Liang Zhao, Yang Wang, Yi Yang +1
This paper presents two unsupervised learning layers (UL layers) for label-free video analysis: one for fully connected layers, and the other for convolutional ones. The proposed U…
Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank
Liang Zhao, Siyu Liao, Yanzhi Wang +4
Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks. Empirical results have shown that neura…