AM-GCN: Adaptive Multi-channel Graph Convolutional Networks

By Xiao Wang, Meiqi Zhu, Deyu Bo, Peng Cui, Chuan Shi, Jian Pei. Knowledge Discovery and Data Mining, 2020

616 citations recorded by the source corpus.

Graph Convolutional Networks (GCNs) have gained great popularity in tackling various analytics tasks on graph and network data. However, some recent studies raise concerns about whether GCNs can optimally integrate node features and topological structures in a complex graph with rich information. In this paper, we first present an experimental investigation. Surprisingly, our experimental results clearly show that the capability of the state-of-the-art GCNs in fusing node features and topological structures is distant from optimal or even satisfactory. The weakness may severely hinder the capability of GCNs in some classification tasks, since GCNs may not be able to adaptively learn some deep correlation information between topological structures and node features. Can we remedy the weakness and design a new type of GCNs that can retain the advantages of the state-of-the-art GCNs and, at the same time, enhance the capability of fusing topological structures and node features substantially? We tackle the challenge and propose an adaptive multi-channel graph convolutional networks for semi-supervised classification (AM-GCN). The central idea is that we extract the specific and common embeddings from node features, topological structures, and their combinations simultaneously, and use the attention mechanism to learn adaptive importance weights of the embeddings. Our extensive experiments on benchmark data sets clearly show that AM-GCN extracts the most correlated information from both node features and topological structures substantially, and improves the classification accuracy with a clear margin.

Subfields: Artificial Intelligence, Molecular Biology, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/00c2fd76b5d2167493ac7bfb4ccb8856ff45b0c0

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. Chuan Shi
2. Xiao Wang
3. Binbin Hu
4. Yanfang Ye
5. Yong Li
6. Yu Zheng
7. Liang Wang
8. Qing He

In Molecular Biology

1. Liang Wang
2. Chuan Shi
3. Xiao Wang
4. Binbin Hu
5. Deyu Bo
6. Guojie Song
7. Huawei Shen
8. Yanqiao Zhu

In Statistical and Nonlinear Physics

1. Chuan Shi
2. Xiao Wang
3. Yanfang Ye
4. Liang Wang
5. Qing He
6. Binbin Hu
7. Deyu Bo
8. Guojie Song

Citations in the corpus

• Beyond Low-frequency Information in Graph Convolutional Networks (2021, background): “Even the raw features, containing both low-and high-frequency information, are alternative solution (Wang et al. 2020b).”
• Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection (2021, background): “From the algorithm side, the challenge comes from the message aggregation of GNNs[11, 16, 38, 43, 44], which may lead to the result that the features of the minority class are diluted.”
• Mining Latent Structures for Multimedia Recommendation (2021, methodology): “There are three categories of GSL methods: metric learning [5, 22, 37], probabilistic modeling [8, 25, 48], and direct optimization approaches [9, 17, 42].”
• Heterogeneous Graph Structure Learning for Graph Neural Networks (2021, background): “The semantic graph is generated depending on the high-order topology structure in HIN, describing the multi-hop structural interactions between two nodes.”
• Sequential Recommendation with Graph Neural Networks (2021, methodology): “Common options for kernel-basedmethods include cosine distance [30, 41], Euclidean distance [38, 43] and Mahalanobis distance [18, 34].”