T2-GNN: Graph Neural Networks for Graphs with Incomplete Features and Structure via Teacher-Student Distillation
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (4) · 4339-4346
DOI: 10.1609/aaai.v37i4.25553 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Cuiying Huo und 5 weiteren Autor:innen. Die Arbeit wurde bisher 50-mal zitiert (Crossref).
Abstract (Originalsprache)
Graph Neural Networks (GNNs) have been a prevailing technique for tackling various analysis tasks on graph data. A key premise for the remarkable performance of GNNs relies on complete and trustworthy initial graph descriptions (i.e., node features and graph structure), which is often not satisfied since real-world graphs are often incomplete due to various unavoidable factors. In particular, GNNs face greater challenges when both node features and graph structure are incomplete at the same time. The existing methods either focus on feature completion or structure completion. They usually rely on the matching relationship between features and structure, or employ joint learning of node representation and feature (or structure) completion in the hope of achieving mutual benefit. However, recent studies confirm that the mutual interference between features and structure leads to the degradation of GNN performance. When both features and structure are incomplete, the mismatch between features and structure caused by the missing randomness exacerbates the interference between the two, which may trigger incorrect completions that negatively affect node representation. To this end, in this paper we propose a general GNN framework based on teacher-student distillation to improve the performance of GNNs on incomplete graphs, namely T2-GNN. To avoid the interference between features and structure, we separately design feature-level and structure-level teacher models to provide targeted guidance for student model (base GNNs, such as GCN) through distillation. Then we design two personalized methods to obtain well-trained feature and structure teachers. To ensure that the knowledge of the teacher model is comprehensively and effectively distilled to the student model, we further propose a dual distillation mode to enable the student to acquire as much expert knowledge as possible. Extensive experiments on eight benchmark datasets demonstrate the effectiveness and robustness of the new framework on graphs with incomplete features and structure.
Zitieren
APA
Huo, C., Jin, D., Li, Y., He, D., Yang, Y., & Wu, L. (2023). T2-GNN: Graph Neural Networks for Graphs with Incomplete Features and Structure via Teacher-Student Distillation. Proceedings of the AAAI Conference on Artificial Intelligence, 37(4), 4339-4346. https://doi.org/10.1609/aaai.v37i4.25553
Vancouver
Huo C, Jin D, Li Y, He D, Yang Y, Wu L. T2-GNN: Graph Neural Networks for Graphs with Incomplete Features and Structure via Teacher-Student Distillation. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(4):4339-4346. doi:10.1609/aaai.v37i4.25553
BibTeX
@article{Huo2023,
author = {Huo, Cuiying and Jin, Di and Li, Yawen and He, Dongxiao and Yang, Yu-Bin and Wu, Lingfei},
title = {T2-GNN: Graph Neural Networks for Graphs with Incomplete Features and Structure via Teacher-Student Distillation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {4},
pages = {4339--4346},
doi = {10.1609/aaai.v37i4.25553}
}
EUVIMED