14 citations · 25 across the 6 of their papers we have counts for
6 papers
Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs
Zichao Yue, Chenhui Deng, Zhiru Zhang
Graph neural networks (GNNs) are widely used for learning node embeddings in graphs, typically adopting a message-passing scheme. This approach, however, leads to the neighbor expl…
Polynormer: Polynomial-Expressive Graph Transformer in Linear Time
Chenhui Deng, Zichao Yue, Zhiru Zhang
Graph transformers (GTs) have emerged as a promising architecture that is theoretically more expressive than message-passing graph neural networks (GNNs). However, typical GT model…
SAGMAN: Stability Analysis of Graph Neural Networks on the Manifolds
Wuxinlin Cheng, Chenhui Deng, Ali Aghdaei +2
Modern graph neural networks (GNNs) can be sensitive to changes in the input graph structure and node features, potentially resulting in unpredictable behavior and degraded perform…
GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks
Chenhui Deng, Xiuyu Li, Zhuo Feng +1
Graph neural networks (GNNs) have been increasingly deployed in various applications that involve learning on non-Euclidean data. However, recent studies show that GNNs are vulnera…
SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation
Wuxinlin Cheng, Chenhui Deng, Zhiqiang Zhao +3
A black-box spectral method is introduced for evaluating the adversarial robustness of a given machine learning (ML) model. Our approach, named SPADE, exploits bijective distance m…
GraphZoom: A multi-level spectral approach for accurate and scalable graph embedding
Chenhui Deng, Zhiqiang Zhao, Yongyu Wang +2
Graph embedding techniques have been increasingly deployed in a multitude of different applications that involve learning on non-Euclidean data. However, existing graph embedding m…