1 code implementation • 2 Mar 2024 • Chenhui Deng, Zichao Yue, Cunxi Yu, Gokce Sarar, Ryan Carey, Rajeev Jain, Zhiru Zhang
In this work we propose HOGA, a novel attention-based model for learning circuit representations in a scalable and generalizable manner.
2 code implementations • 2 Mar 2024 • Chenhui Deng, Zichao Yue, Zhiru Zhang
To enable the base model permutation equivariant, we integrate it with graph topology and node features separately, resulting in local and global equivariant attention models.
Ranked #1 on Node Classification on pokec
no code implementations • 13 Feb 2024 • Wuxinlin Cheng, Chenhui Deng, Ali Aghdaei, Zhiru Zhang, Zhuo Feng
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 performance.
1 code implementation • 30 Jan 2022 • Chenhui Deng, Xiuyu Li, Zhuo Feng, Zhiru Zhang
Graph neural networks (GNNs) have been increasingly deployed in various applications that involve learning on non-Euclidean data.
no code implementations • 29 Sep 2021 • Chenhui Deng, Xiuyu Li, Zhuo Feng, Zhiru Zhang
In this paper, we propose GARNET, a scalable spectral method to boost the adversarial robustness of GNN models for both homophilic and heterophilic graphs.
2 code implementations • 7 Feb 2021 • Wuxinlin Cheng, Chenhui Deng, Zhiqiang Zhao, Yaohui Cai, Zhiru Zhang, Zhuo Feng
A black-box spectral method is introduced for evaluating the adversarial robustness of a given machine learning (ML) model.
1 code implementation • ICLR 2020 • Chenhui Deng, Zhiqiang Zhao, Yongyu Wang, Zhiru Zhang, Zhuo Feng
GraphZoom first performs graph fusion to generate a new graph that effectively encodes the topology of the original graph and the node attribute information.