---
title: "FedCCH: Automatic Personalized Graph Federated Learning for Inter-Client and Intra-Client Heterogeneity"
authors:
  - "Pengfei Jiao"
  - "Zian Zhou"
  - "Meiting Xue"
  - "Huijun Tang"
  - "Zhidong Zhao"
  - "HuaMing Wu"
doi: "10.24963/ijcai.2025/333"
url: "https://ijcai.org/proceedings/2025/333"
pdf: "https://ijcai.org/proceedings/2025/0333.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "2991-2999"
track: "Main Track"
keywords:
  - "Data Mining: DM: Mining heterogenous data"
  - "Data Mining: DM: Mining graphs"
---

# FedCCH: Automatic Personalized Graph Federated Learning for Inter-Client and Intra-Client Heterogeneity

Pengfei Jiao, Zian Zhou, Meiting Xue, Huijun Tang, Zhidong Zhao, HuaMing Wu

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 2991-2999. DOI: [10.24963/ijcai.2025/333](https://doi.org/10.24963/ijcai.2025/333)

## Abstract

Graph federated learning (GFL) is increasingly utilized in domains such as social network analysis and recommendation systems, where non-IID data exist extensively and necessitate a strong emphasis on personalized learning. However, existing methods focus only on the personality among different clients instead of the personality within a client which widely exists in the real social networks, where intra-client personality addresses the heterogeneity of known data, while inter-client personality always tackle client heterogeneity under privacy constraint. In this paper, we propose a novel automatic personalized graph federated learning (PGFL) scheme named FedCCH to capture both inter-client and intra-client heterogeneity. For intra-client heterogeneity, we innovatively propose the learnable Personalized Factor (PF) to automatically normalize each graph representation within clients by learnable parameters, which weakens the impact of non-IID data distribution. For inter-client heterogeneity, we propose a novel hash-based similarity clustering method to generate the hash signature for each client, and then group similar clients for joint training among different clients. Ultimately, we collaboratively train intra-client and inter-client modules to improve the effectiveness of capturing the heterogeneity of the graph data of clients. Experiment results demonstrate that FedCCH outperforms other state-of-the-art baseline methods.