EUVIMEDEUVIMED entdecken
Crossref

Multi-view Graph Representation Learning Beyond Homophily

Bei Lin, You Li, Ning Gui, Zhuopeng Xu, Zhiwu Yu

ACM Transactions on Knowledge Discovery from Data · 30.09.2023 · 17 (8) · 1-21

DOI: 10.1145/3592858 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Knowledge Discovery from Data, online erschienen am 28.06.2023. Verfasst von Bei Lin und 4 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: Science and Technology Research and Development Program Project of China railway group limited, Hangzhou High-Flyer AI Fundamental Research Co., Ltd..

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unsupervised graph representation learning (GRL) aims at distilling diverse graph information into task-agnostic embeddings without label supervision. Due to a lack of support from labels, recent representation learning methods usually adopt self-supervised learning, and embeddings are learned by solving a handcrafted auxiliary task (so-called pretext task). However, partially due to the irregular non-Euclidean data in graphs, the pretext tasks are generally designed under homophily assumptions and cornered in the low-frequency signals, which results in significant loss of other signals, especially high-frequency signals widespread in graphs with heterophily. Motivated by this limitation, we propose a multi-view perspective and the usage of diverse pretext tasks to capture different signals in graphs into embeddings. A novel framework, denoted as Multi-view Graph Encoder (MVGE), is proposed, and a set of key designs are identified. More specifically, a set of new pretext tasks are designed to encode different types of signals, and a straightforward operation is proposed to maintain both the commodity and personalization in both the attribute and the structural levels. Extensive experiments on synthetic and real-world network datasets show that the node representations learned with MVGE achieve significant performance improvements in three different downstream tasks, especially on graphs with heterophily.

Förderung

  • Science and Technology Research and Development Program Project of China railway group limited
  • Hangzhou High-Flyer AI Fundamental Research Co., Ltd.

Zitieren

APA

Lin, B., Li, Y., Gui, N., Xu, Z., & Yu, Z. (2023). Multi-view Graph Representation Learning Beyond Homophily. ACM Transactions on Knowledge Discovery from Data, 17(8), 1-21. https://doi.org/10.1145/3592858

Vancouver

Lin B, Li Y, Gui N, Xu Z, Yu Z. Multi-view Graph Representation Learning Beyond Homophily. ACM Transactions on Knowledge Discovery from Data. 2023;17(8):1-21. doi:10.1145/3592858

BibTeX
@article{Lin2023,
  author = {Lin, Bei and Li, You and Gui, Ning and Xu, Zhuopeng and Yu, Zhiwu},
  title = {Multi-view Graph Representation Learning Beyond Homophily},
  journal = {ACM Transactions on Knowledge Discovery from Data},
  year = {2023},
  volume = {17},
  number = {8},
  pages = {1--21},
  doi = {10.1145/3592858}
}
Kostenlos starten →