Neural Architecture Search for GNN-Based Graph Classification
ACM Transactions on Information Systems · 31.01.2024 · 42 (1) · 1-29
DOI: 10.1145/3584945 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 18.08.2023. Verfasst von Lanning Wei und 3 weiteren Autor:innen. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 82 Literaturangaben. Gefördert von: National Natural Science Foundation of China, CCF-Tencent Open Research Fund.
Abstract (Originalsprache)
Graph classification is an important problem with applications across many domains, for which graph neural networks (GNNs) have been state-of-the-art (SOTA) methods. In the literature, to adopt GNNs for the graph classification task, there are two groups of methods: global pooling and hierarchical pooling. The global pooling methods obtain the graph representation vectors by globally pooling all of the node embeddings together at the end of several GNN layers, whereas the hierarchical pooling methods provide one extra pooling operation between the GNN layers to extract hierarchical information and improve the graph representations. Both global and hierarchical pooling methods are effective in different scenarios. Due to highly diverse applications, it is challenging to design data-specific pooling methods with human expertise. To address this problem, we propose PAS (Pooling Architecture Search) to design adaptive pooling architectures by using the neural architecture search (NAS). To enable the search space design, we propose a unified pooling framework consisting of four modules: Aggregation, Pooling, Readout, and Merge. Two variants, PAS-G and PAS-NE, are provided to design the pooling operations in different scales. A set of candidate operations is designed in the search space using this framework. Then, existing human-designed pooling methods, including global and hierarchical ones, can be incorporated. To enable efficient search, a coarsening strategy is developed to continuously relax the search space, and then a differentiable search method can be adopted. We conduct extensive experiments on six real-world datasets, including the large-scale datasets MR and ogbg-molhiv. Experimental results in this article demonstrate the effectiveness and efficiency of the proposed PAS in designing the pooling architectures for graph classification. The Top-1 performance on two Open Graph Benchmark (OGB) datasets 1 further indicates the utility of PAS when facing diverse realistic data. The implementation of PAS is available at: https://github.com/AutoML-Research/PAS.
Förderung
- National Natural Science Foundation of China
- CCF-Tencent Open Research Fund
Zitieren
APA
Wei, L., Zhao, H., He, Z., & Yao, Q. (2024). Neural Architecture Search for GNN-Based Graph Classification. ACM Transactions on Information Systems, 42(1), 1-29. https://doi.org/10.1145/3584945
Vancouver
Wei L, Zhao H, He Z, Yao Q. Neural Architecture Search for GNN-Based Graph Classification. ACM Transactions on Information Systems. 2024;42(1):1-29. doi:10.1145/3584945
BibTeX
@article{Wei2024,
author = {Wei, Lanning and Zhao, Huan and He, Zhiqiang and Yao, Quanming},
title = {Neural Architecture Search for GNN-Based Graph Classification},
journal = {ACM Transactions on Information Systems},
year = {2024},
volume = {42},
number = {1},
pages = {1--29},
doi = {10.1145/3584945}
}
EUVIMED