Hypergraph Neural Architecture Search

In recent years, Hypergraph Neural Networks (HGNNs) have achieved considerable success by manually designing architectures, which are capable of extracting effective patterns with high-order interactions from non-Euclidean data. However, such mechanism is extremely inefficient, demanding tremendous human efforts to tune diverse model parameters. In this paper, we propose a novel Hypergraph Neural Architecture Search (HyperNAS) to automatically design the optimal HGNNs. The proposed model constructs a search space suitable for hypergraphs, and derives hypergraph architectures through differentiable search strategies. A hypergraph structure-aware distance criterion is introduced as a guideline for obtaining an optimal hypergraph architecture via the leave-one-out method. Experimental results for node classification on benchmark Cora, Citeseer, Pubmed citation networks and hypergraph datasets show that HyperNAS outperforms existing HGNNs models and graph NAS methods.

Authors

• Wei Lin Fujian Provincial Key Laboratory of Big Data Mining and Applications College of Computer Science and Mathematics, Fujian University of Technology
• Xu Peng Xiamen University
• Zhengtao Yu Kunming University of Science and Technology
• Taisong Jin Key Laboratory of Multimedia Trusted Perception and Effcient Computing, Ministry of Education of China, Xiamen University, China School of Informatics, Xiamen University, China Key Laboratory of Oracle Bone Inscriptions Information Processing, Ministry of Education of China, Anyang Normal University, China

Keywords

• DMKM: Graph Mining, Social Network Analysis & Community
• ML: Graph-based Machine Learning
• SO: Other Foundations of Search & Optimization