358 citations · 1.1k across the 59 of their papers we have counts for
16 papers · 1 filter
Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations
Tianxiang Zhao, Wenchao Yu, Suhang Wang +6
Imitation learning has achieved great success in many sequential decision-making tasks, in which a neural agent is learned by imitating collected human demonstrations. However, exi…
Reinforcement Learning Guided Multi-Objective Exam Paper Generation
Yuhu Shang, Xuexiong Luo, Lihong Wang +4
To reduce the repetitive and complex work of instructors, exam paper generation (EPG) technique has become a salient topic in the intelligent education field, which targets at gene…
Understanding and Improving Deep Graph Neural Networks: A Probabilistic Graphical Model Perspective
Jiayuan Chen, Xiang Zhang, Yinfei Xu +3
Recently, graph-based models designed for downstream tasks have significantly advanced research on graph neural networks (GNNs). GNN baselines based on neural message-passing mecha…
Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment
Tianxiang Zhao, Dongsheng Luo, Xiang Zhang +1
Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over recent years. Instance-level GNN explanation aims to discover critic…
TopoImb: Toward Topology-level Imbalance in Learning from Graphs
Tianxiang Zhao, Dongsheng Luo, Xiang Zhang +1
Graph serves as a powerful tool for modeling data that has an underlying structure in non-Euclidean space, by encoding relations as edges and entities as nodes. Despite development…
Personalized Federated Learning via Heterogeneous Modular Networks
Tianchun Wang, Wei Cheng, Dongsheng Luo +5
Personalized Federated Learning (PFL) which collaboratively trains a federated model while considering local clients under privacy constraints has attracted much attention. Despite…
HP-GMN: Graph Memory Networks for Heterophilous Graphs
Junjie Xu, Enyan Dai, Xiang Zhang +1
Graph neural networks (GNNs) have achieved great success in various graph problems. However, most GNNs are Message Passing Neural Networks (MPNNs) based on the homophily assumption…
Link Prediction on Heterophilic Graphs via Disentangled Representation Learning
Shijie Zhou, Zhimeng Guo, Charu Aggarwal +2
Link prediction is an important task that has wide applications in various domains. However, the majority of existing link prediction approaches assume the given graph follows homo…
Synthetic Over-sampling for Imbalanced Node Classification with Graph Neural Networks
Tianxiang Zhao, Xiang Zhang, Suhang Wang
In recent years, graph neural networks (GNNs) have achieved state-of-the-art performance for node classification. However, most existing GNNs would suffer from the graph imbalance…
Towards Faithful and Consistent Explanations for Graph Neural Networks
Tianxiang Zhao, Dongsheng Luo, Xiang Zhang +1
Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over recent years. Instance-level GNN explanation aims to discover critic…
InfoGCL: Information-Aware Graph Contrastive Learning
Dongkuan Xu, Wei Cheng, Dongsheng Luo +2
Various graph contrastive learning models have been proposed to improve the performance of learning tasks on graph datasets in recent years. While effective and prevalent, these mo…
Online Graph Learning in Dynamic Environments
Xiang Zhang
Inferring the underlying graph topology that characterizes structured data is pivotal to many graph-based models when pre-defined graphs are not available. This paper focuses on le…
AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators
Yihang Yin, Qingzhong Wang, Siyu Huang +2
Contrastive learning has been widely applied to graph representation learning, where the view generators play a vital role in generating effective contrastive samples. Most of the…
Controlling Neural Networks with Rule Representations
Sungyong Seo, Sercan O. Arik, Jinsung Yoon +3
We propose a novel training method that integrates rules into deep learning, in a way the strengths of the rules are controllable at inference. Deep Neural Networks with Controllab…
Semi-Supervised Graph-to-Graph Translation
Tianxiang Zhao, Xianfeng Tang, Xiang Zhang +1
Graph translation is very promising research direction and has a wide range of potential real-world applications. Graph is a natural structure for representing relationship and int…
GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks
Tianxiang Zhao, Xiang Zhang, Suhang Wang
Node classification is an important research topic in graph learning. Graph neural networks (GNNs) have achieved state-of-the-art performance of node classification. However, exist…