FedHGPrompt: Privacy-Preserving Federated Prompt Learning for Few-Shot Heterogeneous Graph Learning

Learning from heterogeneous graphs under the constraints of both data scarcity and data privacy presents a significant challenge. While graph prompt learning offers a pathway for efficient few-shot adaptation, and federated learning provides a paradigm for decentralized training, their direct integr...

Täydet tiedot

Bibliografiset tiedot

Päätekijät:	Xijun Wu, Jianjun Shi, Xinming Zhang
Aineistotyyppi:	Artigo
Kieli:	Inglês
Julkaistu:	MDPI AG 2026-01-01
Sarja:	Entropy
Aiheet:	federated learning heterogeneous graphs prompt learning few-shot learning privacy preservation secure aggregation
Linkit:	https://www.mdpi.com/1099-4300/28/2/143
Tagit:	Lisää tagi Ei tageja, Lisää ensimmäinen tagi!