Graph Entropy Guided Node Embedding Dimension Selection for Graph Neural Networks

Graph Entropy Guided Node Embedding Dimension Selection for Graph Neural Networks

Gongxu Luo, Jianxin Li, Hao Peng, Carl Yang, Lichao Sun, Philip S. Yu, Lifang He

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Main Track. Pages 2767-2774. https://doi.org/10.24963/ijcai.2021/381

Graph representation learning has achieved great success in many areas, including e-commerce, chemistry, biology, etc. However, the fundamental problem of choosing the appropriate dimension of node embedding for a given graph still remains unsolved. The commonly used strategies for Node Embedding Dimension Selection (NEDS) based on grid search or empirical knowledge suffer from heavy computation and poor model performance. In this paper, we revisit NEDS from the perspective of minimum entropy principle. Subsequently, we propose a novel Minimum Graph Entropy (MinGE) algorithm for NEDS with graph data. To be specific, MinGE considers both feature entropy and structure entropy on graphs, which are carefully designed according to the characteristics of the rich information in them. The feature entropy, which assumes the embeddings of adjacent nodes to be more similar, connects node features and link topology on graphs. The structure entropy takes the normalized degree as basic unit to further measure the higher-order structure of graphs. Based on them, we design MinGE to directly calculate the ideal node embedding dimension for any graph. Finally, comprehensive experiments with popular Graph Neural Networks (GNNs) on benchmark datasets demonstrate the effectiveness and generalizability of our proposed MinGE.
Keywords:
Machine Learning: Dimensionality Reduction
Data Mining: Mining Graphs, Semi Structured Data, Complex Data
Data Mining: Theoretical Foundation of Data Mining