no code implementations • 20 Mar 2024 • Ningyi Liao, Zihao Yu, Siqiang Luo
Graph Neural Networks (GNNs) have shown promising performance in various graph learning tasks, but at the cost of resource-intensive computations.
1 code implementation • 17 May 2023 • Haoyu Liu, Ningyi Liao, Siqiang Luo
Graph neural networks (GNNs) realize great success in graph learning but suffer from performance loss when meeting heterophily, i. e. neighboring nodes are dissimilar, due to their local and uniform aggregation.
1 code implementation • 19 Jul 2022 • Ningyi Liao, Dingheng Mo, Siqiang Luo, Xiang Li, Pengcheng Yin
Recent advances in data processing have stimulated the demand for learning graphs of very large scales.
1 code implementation • 3 Apr 2022 • Kai Siong Yow, Ningyi Liao, Siqiang Luo, Reynold Cheng, Chenhao Ma, Xiaolin Han
Many algorithms are proposed in studying subgraph problems, where one common approach is by extracting the patterns and structures of a given graph.
no code implementations • 11 Sep 2020 • Shufan Wang, Ningyi Liao, Liyao Xiang, Nanyang Ye, Quanshi Zhang
Through experiments on a variety of adversarial pruning methods, we find that weights sparsity will not hurt but improve robustness, where both weights inheritance from the lottery ticket and adversarial training improve model robustness in network pruning.