Current browse context:
cs.LG
Change to browse by:
References & Citations
Computer Science > Machine Learning
Title: FedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated Learning
(Submitted on 22 Apr 2024 (v1), last revised 25 Apr 2024 (this version, v2))
Abstract: Subgraph federated learning (subgraph-FL) is a new distributed paradigm that facilitates the collaborative training of graph neural networks (GNNs) by multi-client subgraphs. Unfortunately, a significant challenge of subgraph-FL arises from subgraph heterogeneity, which stems from node and topology variation, causing the impaired performance of the global GNN. Despite various studies, they have not yet thoroughly investigated the impact mechanism of subgraph heterogeneity. To this end, we decouple node and topology variation, revealing that they correspond to differences in label distribution and structure homophily. Remarkably, these variations lead to significant differences in the class-wise knowledge reliability of multiple local GNNs, misguiding the model aggregation with varying degrees. Building on this insight, we propose topology-aware data-free knowledge distillation technology (FedTAD), enhancing reliable knowledge transfer from the local model to the global model. Extensive experiments on six public datasets consistently demonstrate the superiority of FedTAD over state-of-the-art baselines.
Submission history
From: Xunkai Li [view email][v1] Mon, 22 Apr 2024 10:19:02 GMT (820kb,D)
[v2] Thu, 25 Apr 2024 06:40:22 GMT (981kb,D)
Link back to: arXiv, form interface, contact.