Tail-GNN: Tail-node graph neural networks
Publication Type
Conference Proceeding Article
Publication Date
8-2021
Abstract
The prevalence of graph structures in real-world scenarios enables important tasks such as node classification and link prediction. Graphs in many domains follow a long-tailed distribution in their node degrees, i.e., a significant fraction of nodes are tail nodes with a small degree. Although recent graph neural networks (GNNs) can learn powerful node representations, they treat all nodes uniformly and are not tailored to the large group of tail nodes. In particular, there is limited structural information (i.e., links) on tail nodes, resulting in inferior performance. Toward robust tail node embedding, in this paper we propose a novel graph neural network called Tail-GNN. It hinges on the novel concept of transferable neighborhood translation, to model the variable ties between a target node and its neighbors. On one hand, Tail-GNN learns a neighborhood translation from the structurally rich head nodes (i.e., high-degree nodes), which can be further transferred to the structurally limited tail nodes to enhance their representations. On the other hand, the ties with the neighbors are variable across different parts of the graph, and a global neighborhood translation is inflexible. Thus, we devise a node-wise adaptation to localize the global translation w.r.t. each node. Extensive experiments on five benchmark datasets demonstrate that our proposed Tail-GNN significantly outperforms the state-of-the-art baselines.
Keywords
Graph neural networks, tail node embedding, transferable neighborhood translation
Discipline
Graphics and Human Computer Interfaces
Research Areas
Intelligent Systems and Optimization
Publication
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Singapore, August 14-18
First Page
1109
Last Page
1119
Identifier
10.1145/3447548.3467276
Publisher
ACM
City or Country
New York
Citation
LIU, Zemin; NGUYEN, Trung Kien; and FANG, Yuan.
Tail-GNN: Tail-node graph neural networks. (2021). KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Singapore, August 14-18. 1109-1119.
Available at: https://ink.library.smu.edu.sg/sis_research/10831
Additional URL
https://doi.org/10.1145/3447548.3467276