Federated Graph Classification over Non-IID Graphs

TL;DR

This paper introduces a federated learning framework for graph classification that addresses non-IID data across local systems by dynamically clustering graphs based on GNN gradients, improving model training.

Contribution

It proposes a novel graph clustered federated learning (GCFL) framework with a gradient sequence-based clustering method (GCFL+), handling heterogeneity in non-IID graph data.

Findings

GCFL effectively reduces heterogeneity among local graph datasets.

GCFL+ improves clustering accuracy with gradient sequence analysis.

Experimental results show enhanced graph classification performance.

Abstract

Federated learning has emerged as an important paradigm for training machine learning models in different domains. For graph-level tasks such as graph classification, graphs can also be regarded as a special type of data samples, which can be collected and stored in separate local systems. Similar to other domains, multiple local systems, each holding a small set of graphs, may benefit from collaboratively training a powerful graph mining model, such as the popular graph neural networks (GNNs). To provide more motivation towards such endeavors, we analyze real-world graphs from different domains to confirm that they indeed share certain graph properties that are statistically significant compared with random graphs. However, we also find that different sets of graphs, even from the same domain or same dataset, are non-IID regarding both graph structures and node features. To handle this, we propose a graph clustered federated learning (GCFL) framework that dynamically finds clusters of local systems based on the gradients of GNNs, and theoretically justify that such clusters can reduce the structure and feature heterogeneity among graphs owned by the local systems. Moreover, we observe the gradients of GNNs to be rather fluctuating in GCFL which impedes high-quality clustering, and design a gradient sequence-based clustering mechanism based on dynamic time warping (GCFL+). Extensive experimental results and in-depth analysis demonstrate the effectiveness of our proposed frameworks.