Timezone: »
Graph Convolutional Network and many of its variants are known to suffer from the dilemma between model depth and over-smoothing issues. Stacking layers of GCN usually lead to the exponential expansion of the receptive field (i.e., high-order neighbors). In order to incorporate the information from high-order neighbors to learn node representations without drastically increasing the number of graph convolution layers, we propose a simple and effective pre-processing technique to increase graph connectivity. Our approach selectively inserts connections between center nodes and informative high-order neighbors, with learnable weights to control the information flow through the connection. Experiments show that our approach improves the performance of GCN, and reduce the depth of GCNII without sacrificing its performance. Besides, our proposed homophily-based weight assignment can mitigate the effect of graph structural attacks.
Author Information
Songtao Liu (The Pennsylvania State University)
Shixiong Jing (Penn State University)
Tong Zhao (Snap Inc.)
Zengfeng Huang (Fudan University)
Dinghao Wu (Pennsylvania State University)
More from the Same Authors
-
2022 Poster: Optimal Clustering with Noisy Queries via Multi-Armed Bandit »
Jinghui Xia · Zengfeng Huang -
2022 Spotlight: Optimal Clustering with Noisy Queries via Multi-Armed Bandit »
Jinghui Xia · Zengfeng Huang -
2022 Poster: Local Augmentation for Graph Neural Networks »
Songtao Liu · Rex (Zhitao) Ying · Hanze Dong · Lanqing Li · Tingyang Xu · Yu Rong · Peilin Zhao · Junzhou Huang · Dinghao Wu -
2022 Spotlight: Local Augmentation for Graph Neural Networks »
Songtao Liu · Rex (Zhitao) Ying · Hanze Dong · Lanqing Li · Tingyang Xu · Yu Rong · Peilin Zhao · Junzhou Huang · Dinghao Wu -
2022 Poster: Learning from Counterfactual Links for Link Prediction »
Tong Zhao · Gang Liu · Daheng Wang · Wenhao Yu · Meng Jiang -
2022 Spotlight: Learning from Counterfactual Links for Link Prediction »
Tong Zhao · Gang Liu · Daheng Wang · Wenhao Yu · Meng Jiang -
2021 Poster: Graph Neural Networks Inspired by Classical Iterative Algorithms »
Yang Yongyi · Tang Liu · Yangkun Wang · Jinjing Zhou · Quan Gan · Zhewei Wei · Zheng Zhang · Zengfeng Huang · David Wipf -
2021 Oral: Graph Neural Networks Inspired by Classical Iterative Algorithms »
Yang Yongyi · Tang Liu · Yangkun Wang · Jinjing Zhou · Quan Gan · Zhewei Wei · Zheng Zhang · Zengfeng Huang · David Wipf -
2020 Poster: Simple and Deep Graph Convolutional Networks »
Ming Chen · Zhewei Wei · Zengfeng Huang · Bolin Ding · Yaliang Li