{"type":"ScholarlyArticle","title":"FedCCH: Automatic Personalized Graph Federated Learning for Inter-Client and Intra-Client Heterogeneity","authors":[{"name":"Pengfei Jiao","slug":"pengfei-jiao","given":"Pengfei","family":"Jiao","affiliation":""},{"name":"Zian Zhou","slug":"zian-zhou","given":"Zian","family":"Zhou","affiliation":""},{"name":"Meiting Xue","slug":"meiting-xue","given":"Meiting","family":"Xue","affiliation":""},{"name":"Huijun Tang","slug":"huijun-tang","given":"Huijun","family":"Tang","affiliation":""},{"name":"Zhidong Zhao","slug":"zhidong-zhao","given":"Zhidong","family":"Zhao","affiliation":""},{"name":"HuaMing Wu","slug":"huaming-wu","given":"HuaMing","family":"Wu","affiliation":""}],"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.","doi":"10.24963/ijcai.2025/333","url":"https://ijcai.org/proceedings/2025/333","pdf":"https://ijcai.org/proceedings/2025/0333.pdf","markdown":"https://ijcai.org/proceedings/2025/333.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/333","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Data Mining","track":"Main Track","number":333,"pages":{"first":2991,"last":2999},"keywords":["Data Mining: DM: Mining heterogenous data","Data Mining: DM: Mining graphs"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}