activity
20122022
most citedHyper-Sphere Quantization: Communication-Efficient SGD for Federated Learning

32 citations · 139 across the 14 of their papers we have counts for

collaborators
Showing cs.LGShow all

15 papers · 1 filter

cs.LG2022

DGI: Easy and Efficient Inference for GNNs

Peiqi Yin, Xiao Yan, Jinjing Zhou +5

While many systems have been developed to train Graph Neural Networks (GNNs), efficient model inference and evaluation remain to be addressed. For instance, using the widely adopte…

cs.LG202226 cited

Understanding and Improving Graph Injection Attack by Promoting Unnoticeability

Yongqiang Chen, Han Yang, Yonggang Zhang +4

Recently Graph Injection Attack (GIA) emerges as a practical attack scenario on Graph Neural Networks (GNNs), where the adversary can merely inject few malicious nodes instead of m…

cs.LG2020

Rethinking Graph Regularization for Graph Neural Networks

Han Yang, Kaili Ma, James Cheng

The graph Laplacian regularization term is usually used in semi-supervised representation learning to provide graph structure information for a model . However, with the rece…

cs.LG202012 cited

Understanding Graph Neural Networks from Graph Signal Denoising Perspectives

Guoji Fu, Yifan Hou, Jian Zhang +3

Graph neural networks (GNNs) have attracted much attention because of their excellent performance on tasks such as node classification. However, there is inadequate understanding o…

cs.LG2020

Boosting First-Order Methods by Shifting Objective: New Schemes with Faster Worst-Case Rates

Kaiwen Zhou, Anthony Man-Cho So, James Cheng

We propose a new methodology to design first-order methods for unconstrained strongly convex problems. Specifically, instead of tackling the original objective directly, we constru…

cs.LG2020

Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs

Han Yang, Xiao Yan, Xinyan Dai +2

Graph neural networks (GNNs) have received much attention recently because of their excellent performance on graph-based tasks. However, existing research on GNNs focuses on design…