Collaboration in Participant-Centric Federated Learning: A Game-Theoretical Perspective
Collaboration in Participant-Centric Federated Learning: A Game-Theoretical Perspective
复制标题
以参与者为中心的联合学习中的协作：博弈论的视角
DOI：
10.1109/tmc.2022.3194198
复制
发表时间：
2022-07
影响因子：
7.9
通讯作者：
Guangjing Huang;Xu Chen;Ouyang Tao;Qian Ma;Lin Chen;Junshan Zhang
中科院分区：
文献类型：
--
作者：
Guangjing Huang;Xu Chen;Ouyang Tao;Qian Ma;Lin Chen;Junshan Zhang
联邦学习（FL）是一种很有前途的分布式框架，用于协同人工智能模型训练，同时保护用户隐私。一个吸引了大量研究关注的引导组件是激励机制的设计，以刺激FL中的用户协作。大多数工作采用以经纪人为中心的方法来帮助中央操作员吸引参与者，并进一步获得训练有素的模型。很少有研究考虑在参与者之间建立以参与者为中心的合作，以追求共同利益的FL模型，这导致了与以经纪人为中心的FL在激励机制设计上的巨大差异。为了协调自私和异质性的参与者，我们提出了一个新的分析框架来激励以参与者为中心的FL的有效和高效的合作。我们分别针对贡献无关型（COFL）和贡献感知型（CAFL）提出了两种新的博弈模型，其中贡献感知型（CAFL）实现了最小贡献阈值机制。我们进一步分析了COFL和CAFL博弈的纳什均衡的唯一性和存在性，并设计了有效的算法来实现均衡解。广泛的绩效评估表明，COFL存在搭便车现象，采用优化最小阈值的CAFL模型可以极大地缓解这一现象。
Federated learning (FL) is a promising distributed framework for collaborative artificial intelligence model training while protecting user privacy. A bootstrapping component that has attracted significant research attention is the design of incentive mechanism to stimulate user collaboration in FL. The majority of works adopt a broker-centric approach to help the central operator to attract participants and further obtain a well-trained model. Few works consider forging participant-centric collaboration among participants to pursue an FL model for their common interests, which induces dramatic differences in incentive mechanism design from the broker-centric FL. To coordinate the selfish and heterogeneous participants, we propose a novel analytic framework for incentivizing effective and efficient collaborations for participant-centric FL. Specifically, we respectively propose two novel game models for contribution-oblivious FL (COFL) and contribution-aware FL (CAFL), where the latter one implements a minimum contribution threshold mechanism. We further analyze the uniqueness and existence for Nash equilibrium of both COFL and CAFL games and design efficient algorithms to achieve equilibrium solutions. Extensive performance evaluations show that there exists free-riding phenomenon in COFL, which can be greatly alleviated through the adoption of CAFL model with the optimized minimum threshold.