Federated Node Classification over Graphs with Latent Link-type Heterogeneity

Federated learning (FL) aims to train powerful and generalized global models without putting distributed data together, which has been shown effective in various domains of machine learning. The non-IIDness of data across local clients has been a major challenge for FL. In graphs, one specifically i...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings of the ... International World-Wide Web Conference. International WWW Conference Jg. 2023; S. 556
Hauptverfasser: Xie, Han, Xiong, Li, Yang, Carl
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Netherlands 01.01.2023
Schlagworte:
graph mining
graph neural networks
clustering
link-type heterogeneity
federated learning
Online-Zugang:Weitere Angaben
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Federated learning (FL) aims to train powerful and generalized global models without putting distributed data together, which has been shown effective in various domains of machine learning. The non-IIDness of data across local clients has been a major challenge for FL. In graphs, one specifically important perspective of non-IIDness is manifested in the link-type heterogeneity underlying homogeneous graphs- the seemingly uniform links captured in most real-world networks can carry different levels of homophily or semantics of relations, while the exact sets and distributions of such latent link-types can further differ across local clients. Through our preliminary data analysis, we are motivated to design a new graph FL framework that can simultaneously discover latent link-types and model message-passing w.r.t. the discovered link-types through the collaboration of distributed local clients. Specifically, we propose a framework FedLit that can dynamically detect the latent link-types during FL via an EM-based clustering algorithm and differentiate the message-passing through different types of links via multiple convolution channels. For experiments, we synthesize multiple realistic datasets of graphs with latent heterogeneous link-types from real-world data, and partition them with different levels of link-type heterogeneity. Comprehensive experimental results and in-depth analysis have demonstrated both superior performance and rational behaviors of our proposed techniques.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
DOI:10.1145/3543507.3583471