LGAIDBSIApr 22, 2024

FedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated Learning

arXiv:2404.14061v230 citationsh-index: 16IJCAI
Originality Incremental advance
AI Analysis

This addresses performance degradation in distributed graph neural network training due to subgraph heterogeneity, representing an incremental improvement in federated learning for graph data.

The paper tackled the problem of subgraph heterogeneity impairing global graph neural network performance in subgraph federated learning by proposing FedTAD, a topology-aware data-free knowledge distillation method, which achieved superior results over state-of-the-art baselines across six public datasets.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes