EUVIMEDEUVIMED entdecken
Crossref

Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating

Yixin Liu, Yizhen Zheng, Daokun Zhang, Vincent CS Lee, Shirui Pan

Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (4) · 4516-4524

DOI: 10.1609/aaai.v37i4.25573 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Yixin Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 60-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unsupervised graph representation learning (UGRL) has drawn increasing research attention and achieved promising results in several graph analytic tasks. Relying on the homophily assumption, existing UGRL methods tend to smooth the learned node representations along all edges, ignoring the existence of heterophilic edges that connect nodes with distinct attributes. As a result, current methods are hard to generalize to heterophilic graphs where dissimilar nodes are widely connected, and also vulnerable to adversarial attacks. To address this issue, we propose a novel unsupervised Graph Representation learning method with Edge hEterophily discriminaTing (GREET) which learns representations by discriminating and leveraging homophilic edges and heterophilic edges. To distinguish two types of edges, we build an edge discriminator that infers edge homophily/heterophily from feature and structure information. We train the edge discriminator in an unsupervised way through minimizing the crafted pivot-anchored ranking loss, with randomly sampled node pairs acting as pivots. Node representations are learned through contrasting the dual-channel encodings obtained from the discriminated homophilic and heterophilic edges. With an effective interplaying scheme, edge discriminating and representation learning can mutually boost each other during the training phase. We conducted extensive experiments on 14 benchmark datasets and multiple learning scenarios to demonstrate the superiority of GREET.

Zitieren

APA

Liu, Y., Zheng, Y., Zhang, D., Lee, V. C., & Pan, S. (2023). Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating. Proceedings of the AAAI Conference on Artificial Intelligence, 37(4), 4516-4524. https://doi.org/10.1609/aaai.v37i4.25573

Vancouver

Liu Y, Zheng Y, Zhang D, Lee VC, Pan S. Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(4):4516-4524. doi:10.1609/aaai.v37i4.25573

BibTeX
@article{Liu2023,
  author = {Liu, Yixin and Zheng, Yizhen and Zhang, Daokun and Lee, Vincent CS and Pan, Shirui},
  title = {Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2023},
  volume = {37},
  number = {4},
  pages = {4516--4524},
  doi = {10.1609/aaai.v37i4.25573}
}
Kostenlos starten →