Dec 20, 2023 · This paper presents a novel incentive mechanism tailored for fair graph federated learning, integrating incentives derived from both model gradient and payoff.
scholar.google.com › citations
Graph federated learning (FL) has emerged as a pivotal paradigm enabling multiple agents to collaboratively train a graph model while preserving local data ...
Our goal is to enhance fairness in graph federation by combining model gradients and payoff allocation mechanisms (Table 1) to reward contributing agents, ...
This is the Pytorch implementation of the paper "Towards Fair Graph Federated Learning via Incentive Mechanisms" accepted by AAAI-2024.
Oct 22, 2024 · In view of this, this paper presents a novel incentive mechanism tailored for fair graph federated learning, integrating incentives derived from ...
A novel incentive mechanism tailored for fair graph federated learning, integrating incentives derived from both model gradient and payoff is presented, ...
To address this issue, we propose a novel vertical federated social recommendation method leveraging privacy-preserving two-party graph convolution networks ( ...
Incentives. Conference Paper. Towards Fair Graph Federated Learning via Incentive Mechanisms. January 2024. Authors: Chenglu Pan at Zhejiang University.
Technical paper AAAI 2024 • February 24, 2024 • Vancouver , Canada Towards Fair Graph Federated Learning via Incentive Mechanisms
Towards Fair Graph Federated Learning via Incentive Mechanisms ... Extensive experiments show that our model achieves the best trade-off between accuracy and the ...