EUVIMEDEUVIMED entdecken
Crossref

Neighbor Contrastive Learning on Learnable Graph Augmentation

Xiao Shen, Dewang Sun, Shirui Pan, Xi Zhou, Laurence T. Yang

Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (8) · 9782-9791

DOI: 10.1609/aaai.v37i8.26168 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Xiao Shen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 118-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent years, graph contrastive learning (GCL), which aims to learn representations from unlabeled graphs, has made great progress. However, the existing GCL methods mostly adopt human-designed graph augmentations, which are sensitive to various graph datasets. In addition, the contrastive losses originally developed in computer vision have been directly applied to graph data, where the neighboring nodes are regarded as negatives and consequently pushed far apart from the anchor. However, this is contradictory with the homophily assumption of net-works that connected nodes often belong to the same class and should be close to each other. In this work, we propose an end-to-end automatic GCL method, named NCLA to apply neighbor contrastive learning on learnable graph augmentation. Several graph augmented views with adaptive topology are automatically learned by the multi-head graph attention mechanism, which can be compatible with various graph datasets without prior domain knowledge. In addition, a neighbor contrastive loss is devised to allow multiple positives per anchor by taking network topology as the supervised signals. Both augmentations and embeddings are learned end-to-end in the proposed NCLA. Extensive experiments on the benchmark datasets demonstrate that NCLA yields the state-of-the-art node classification performance on self-supervised GCL and even exceeds the supervised ones, when the labels are extremely limited. Our code is released at https://github.com/shenxiaocam/NCLA.

Zitieren

APA

Shen, X., Sun, D., Pan, S., Zhou, X., & Yang, L. T. (2023). Neighbor Contrastive Learning on Learnable Graph Augmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 37(8), 9782-9791. https://doi.org/10.1609/aaai.v37i8.26168

Vancouver

Shen X, Sun D, Pan S, Zhou X, Yang LT. Neighbor Contrastive Learning on Learnable Graph Augmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(8):9782-9791. doi:10.1609/aaai.v37i8.26168

BibTeX
@article{Shen2023,
  author = {Shen, Xiao and Sun, Dewang and Pan, Shirui and Zhou, Xi and Yang, Laurence T.},
  title = {Neighbor Contrastive Learning on Learnable Graph Augmentation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2023},
  volume = {37},
  number = {8},
  pages = {9782--9791},
  doi = {10.1609/aaai.v37i8.26168}
}
Kostenlos starten →