English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Federated Graph Learning (FGL) is a distributed machine learning paradigmthat enables collaborative training on large-scale subgraphs across multiplelocal systems. Existing FGL studies fall into two categories: (i) FGLOptimization, which improves multi-client training in existing machine learningmodels; (ii) FGL Model, which enhances performance with complex local modelsand multi-client interactions. However, most FGL optimization strategies aredesigned specifically for the computer vision domain and ignore graphstructure, presenting dissatisfied performance and slow convergence. Meanwhile,complex local model architectures in FGL Models studies lack scalability forhandling large-scale subgraphs and have deployment limitations. To addressthese issues, we propose Federated Graph Topology-aware Aggregation (FedGTA), apersonalized optimization strategy that optimizes through topology-aware localsmoothing confidence and mixed neighbor features. During experiments, we deployFedGTA in 12 multi-scale real-world datasets with the Louvain and Metis split.This allows us to evaluate the performance and robustness of FedGTA across arange of scenarios. Extensive experiments demonstrate that FedGTA achievesstate-of-the-art performance while exhibiting high scalability and efficiency.The experiment includes ogbn-papers100M, the most representative large-scalegraph database so that we can verify the applicability of our method tolarge-scale graph learning. To the best of our knowledge, our study is thefirst to bridge large-scale graph learning with FGL using this optimizationstrategy, contributing to the development of efficient and scalable FGLmethods.

FedGTA: Topology-aware Averaging for Federated Graph Learning