1.2k citations · 4.2k across the 61 of their papers we have counts for
22 papers · 1 filter
SAILOR: Structural Augmentation Based Tail Node Representation Learning
Jie Liao, Jintang Li, Liang Chen +3
Graph Neural Networks (GNNs) have achieved state-of-the-art performance in representation learning for graphs recently. However, the effectiveness of GNNs, which capitalize on the…
Oversmoothing: A Nightmare for Graph Contrastive Learning?
Jintang Li, Wangbin Sun, Ruofan Wu +3
Oversmoothing is a common phenomenon observed in graph neural networks (GNNs), in which an increase in the network depth leads to a deterioration in their performance. Graph contra…
Less Can Be More: Unsupervised Graph Pruning for Large-scale Dynamic Graphs
Jintang Li, Sheng Tian, Ruofan Wu +6
The prevalence of large-scale graphs poses great challenges in time and storage for training and deploying graph neural networks (GNNs). Several recent works have explored solution…
HyperTuner: A Cross-Layer Multi-Objective Hyperparameter Auto-Tuning Framework for Data Analytic Services
Hui Dou, Shanshan Zhu, Yiwen Zhang +2
Hyper-parameters optimization (HPO) is vital for machine learning models. Besides model accuracy, other tuning intentions such as model training time and energy consumption are als…
Spectral Adversarial Training for Robust Graph Neural Network
Jintang Li, Jiaying Peng, Liang Chen +3
Recent studies demonstrate that Graph Neural Networks (GNNs) are vulnerable to slight but adversarially designed perturbations, known as adversarial examples. To address this issue…
FedEgo: Privacy-preserving Personalized Federated Graph Learning with Ego-graphs
Taolin Zhang, Chuan Chen, Yaomin Chang +2
As special information carriers containing both structure and feature information, graphs are widely used in graph mining, e.g., Graph Neural Networks (GNNs). However, in some prac…
A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection
Bingzhe Wu, Jintang Li, Junchi Yu +17
Deep graph learning has achieved remarkable progresses in both business and scientific areas ranging from finance and e-commerce, to drug and advanced material discovery. Despite t…
FastGCL: Fast Self-Supervised Learning on Graphs via Contrastive Neighborhood Aggregation
Yuansheng Wang, Wangbin Sun, Kun Xu +3
Graph contrastive learning (GCL), as a popular approach to graph self-supervised learning, has recently achieved a non-negligible effect. To achieve superior performance, the major…
What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders
Jintang Li, Ruofan Wu, Wangbin Sun +6
The last years have witnessed the emergence of a promising self-supervised learning strategy, referred to as masked autoencoding. However, there is a lack of theoretical understand…
GUARD: Graph Universal Adversarial Defense
Jintang Li, Jie Liao, Ruofan Wu +5
Graph convolutional networks (GCNs) have been shown to be vulnerable to small adversarial perturbations, which becomes a severe threat and largely limits their applications in secu…
Recent Advances in Reliable Deep Graph Learning: Inherent Noise, Distribution Shift, and Adversarial Attack
Jintang Li, Bingzhe Wu, Chengbin Hou +5
Deep graph learning (DGL) has achieved remarkable progress in both business and scientific areas ranging from finance and e-commerce to drug and advanced material discovery. Despit…
Understanding Structural Vulnerability in Graph Convolutional Networks
Liang Chen, Jintang Li, Qibiao Peng +3
Recent studies have shown that Graph Convolutional Networks (GCNs) are vulnerable to adversarial attacks on the graph structure. Although multiple works have been proposed to impro…
A Decentralized Federated Learning Framework via Committee Mechanism with Convergence Guarantee
Chunjiang Che, Xiaoli Li, Chuan Chen +2
Federated learning allows multiple participants to collaboratively train an efficient model without exposing data privacy. However, this distributed machine learning training metho…
FedGL: Federated Graph Learning Framework with Global Self-Supervision
Chuan Chen, Weibo Hu, Ziyue Xu +1
Graph data are ubiquitous in the real world. Graph learning (GL) tries to mine and analyze graph data so that valuable information can be discovered. Existing GL methods are design…
MG-GCN: Fast and Effective Learning with Mix-grained Aggregators for Training Large Graph Convolutional Networks
Tao Huang, Yihan Zhang, Jiajing Wu +2
Graph convolutional networks (GCNs) have been employed as a kind of significant tool on many graph-based applications recently. Inspired by convolutional neural networks (CNNs), GC…
Ensemble Knowledge Distillation for CTR Prediction
Jieming Zhu, Jinyang Liu, Weiqi Li +4
Recently, deep learning-based models have been widely studied for click-through rate (CTR) prediction and lead to improved prediction accuracy in many industrial applications. Howe…
Adversarial Attack on Large Scale Graph
Jintang Li, Tao Xie, Liang Chen +3
Recent studies have shown that graph neural networks (GNNs) are vulnerable against perturbations due to lack of robustness and can therefore be easily fooled. Currently, most works…
An Uncoupled Training Architecture for Large Graph Learning
Dalong Yang, Chuan Chen, Youhao Zheng +2
Graph Convolutional Network (GCN) has been widely used in graph learning tasks. However, GCN-based models (GCNs) is an inherently coupled training framework repetitively conducting…
A Survey of Adversarial Learning on Graphs
Liang Chen, Jintang Li, Jiaying Peng +6
Deep learning models on graphs have achieved remarkable performance in various graph analysis tasks, e.g., node classification, link prediction, and graph clustering. However, they…
Prophet: Proactive Candidate-Selection for Federated Learning by Predicting the Qualities of Training and Reporting Phases
Huawei Huang, Kangying Lin, Song Guo +2
Although the challenge of the device connection is much relieved in 5G networks, the training latency is still an obstacle preventing Federated Learning (FL) from being largely ado…
Towards Better Forecasting by Fusing Near and Distant Future Visions
Jiezhu Cheng, Kaizhu Huang, Zibin Zheng
Multivariate time series forecasting is an important yet challenging problem in machine learning. Most existing approaches only forecast the series value of one future moment, igno…
Collaborative Deep Learning Across Multiple Data Centers
Kele Xu, Haibo Mi, Dawei Feng +4
Valuable training data is often owned by independent organizations and located in multiple data centers. Most deep learning approaches require to centralize the multi-datacenter da…