Node Similarity Preserving Graph Convolutional Networks

By Wei Jin, Tyler Derr, Yiqi Wang, Yao Ma, Zitao Liu, Jiliang Tang. Web Search and Data Mining, 2020

328 citations recorded by the source corpus.

Graph Neural Networks (GNNs) have achieved tremendous success in various real-world applications due to their strong ability in graph representation learning. GNNs explore the graph structure and node features by aggregating and transforming information within node neighborhoods. However, through theoretical and empirical analysis, we reveal that the aggregation process of GNNs tends to destroy node similarity in the original feature space. There are many scenarios where node similarity plays a crucial role. Thus, it has motivated the proposed framework SimP-GCN that can effectively and efficiently preserve node similarity while exploiting graph structure. Specifically, to balance information from graph structure and node features, we propose a feature similarity preserving aggregation which adaptively integrates graph structure and node features. Furthermore, we employ self-supervised learning to explicitly capture the complex feature similarity and dissimilarity relations between nodes. We validate the effectiveness of SimP-GCN on seven benchmark datasets including three assortative and four disassorative graphs. The results demonstrate that SimP-GCN outperforms representative baselines. Further probe shows various advantages of the proposed framework. The implementation of SimP-GCN is available at https://github.com/ChandlerBang/SimP-GCN.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems

View Paper: https://www.semanticscholar.org/paper/792a9914cbaacbab1ce2e5de9a7f5eee3afb9766

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Philip S. Yu
2. Lichao Sun
3. Chuan Zhou
4. Feng Xia
5. Shirui Pan
6. Yaochen Xie
7. Zhengyang Wang
8. Zhao Xu

In Computer Vision and Pattern Recognition

1. Philip S. Yu
2. Ser-Nam Lim
3. Bo Li
4. Shirui Pan
5. Dacheng Tao
6. Shuiwang Ji
7. Chuan Zhou
8. Luc Van Gool

In Information Systems

1. Shirui Pan
2. Bo Li
3. Philip S. Yu
4. Shuiwang Ji
5. Chuan Zhou
6. Yixin Liu
7. Ser-Nam Lim
8. Lichao Sun

Citations in the corpus

• Graph Self-Supervised Learning: A Survey (2021, methodology): “Similar to PairwiseAttrSim, SimP-GCN [58] also considers predicting the cosine”
• Adversarial Attack and Defense on Graph Data: A Survey (2018, methodology): “[65] 2021 WSDM GNN Metattack Information aggregation based on feature similarity GCN, GAT, Pro-GNN, GCN-Jaccard Accuracy Cora, Citeseer, Pubmed”
• Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods (2021, background): “Various GNNs have been proposed to achieve higher performance in low-homophily settings [82, 44, 81, 17, 15, 73, 36, 35].”
• Self-Supervised Learning of Graph Neural Networks: A Unified Review (2021, methodology): “Similarly, SimP-GCN [88] applies node-pair similarity as a substitute of the adjacency matrix to construct a self-supervised auxiliary task.”