{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:37:59Z","timestamp":1761176279292,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>Generative Adversarial Networks (GANs) have achieved remarkable success in data synthesis tasks, but centralized training methods inherently pose risks of sensitive data exposure. Federated Generative Adversarial Networks (FedGANs) provide a privacy-preserving solution by enabling collaborative model training across distributed clients without exchanging raw data. However, existing FedGAN frameworks face significant challenges in practical scenarios involving non-independent and identically distributed (non-IID) client data and heterogeneous model architectures, often leading to degraded generation quality, mode collapse, and potential privacy risks. To address these issues, we propose HPA-FedGAN, a FedGAN framework leveraging hierarchical prototype alignment. Instead of directly aggregating model parameters, HPA-FedGAN abstracts local features into multi-granularity prototypes, which are aggregated on the server to form global prototypes. Clients then hierarchically align their local prototypes with the global ones, guiding local models toward consistent approximation of the global data distribution. This design enhances generation quality and diversity while improving privacy protection through feature abstraction. Experimental results demonstrate that in complex scenarios where model heterogeneity and Non-IID data coexist, the HPA-FedGAN framework achieves significant performance improvements over state-of-the-art methods.<\/jats:p>","DOI":"10.3233\/faia251349","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:59:04Z","timestamp":1761127144000},"source":"Crossref","is-referenced-by-count":0,"title":["HPA-FedGAN: Federated Generative Adversarial Network Based on Hierarchical Prototype Alignment"],"prefix":"10.3233","author":[{"given":"Zhigang","family":"Wang","sequence":"first","affiliation":[{"name":"College of Computer Science, Inner Mongolia University, Hohhot, Inner Mongolia, 01002, China"}]},{"given":"Xinhao","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Inner Mongolia University, Hohhot, Inner Mongolia, 01002, China"}]},{"given":"Shihao","family":"Yan","sequence":"additional","affiliation":[{"name":"College of Computer Science, Inner Mongolia University, Hohhot, Inner Mongolia, 01002, China"}]},{"given":"Junfeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Computer Science, Inner Mongolia University, Hohhot, Inner Mongolia, 01002, China"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA251349","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:59:04Z","timestamp":1761127144000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA251349"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia251349","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}