Coalitional Game Theoretic Federated Learning
Coalitional Game Theoretic Federated Learning
复制标题
DOI：
10.1109/wi-iat55865.2022.00017
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Masato Ota;Y. Sakurai;Satoshi Oyama
中科院分区：
文献类型：
--
作者：
Masato Ota;Y. Sakurai;Satoshi Oyama
本研究从联盟博弈的观点探讨联邦学习（FL）与联盟结构生成（CSG）。在传统的FL中，即使每个客户端都有来自不同分布的数据，他们仍然学习单个全局模型。然而，每个局部模型的性能可能会降低。为了解决这些问题，我们提出了一种算法，在该算法中，客户端形成联盟和客户端在同一个联盟共同训练一个专门的模型的联盟，即联盟模型。我们制定的算法作为一个图形化的联盟游戏给出了一个加权的无向图，其中一个节点表示一个客户端和边的权重表示两个连接的客户端之间的协同作用。制定FL作为一个CSG问题，使我们能够产生一个最佳的CS，最大限度地提高协同效应的总和。我们首先定义两种类型的协同作用，即，该算法基于两个智能体加入同一联盟时分类准确度的平均提高，以及基于损失函数梯度之间的余弦相似性，旨在将具有敌对数据的对手从一组非对手中排除。我们进行了实验来评估我们的算法，结果表明，它优于现有的算法。
This study approaches federated learning (FL) from the viewpoint of coalitional games with coalition structure generation (CSG). In conventional FL, even if each client has data from a different distribution, they still learn a single global model. However, the performance of each local model can degrade. To address such issues, we propose an algorithm in which clients form coalitions and the clients in the same coalition jointly train a specialized model for the coalition, namely a coalition model. We formulate the algorithm as a graphical coalition game given by a weighted undirected graph in which a node indicates a client and the weight of an edge indicates the synergy between two connected clients. Formulating FL as a CSG problem enables us to generate an optimal CS that maximizes the sum of synergies. We first define two types of synergy, i.e., that based on the average improvement in classification accuracy of two agents as they join the same coalition and that based on the cosine similarity between the gradients of the loss functions, which is intended to exclude adversaries having adversarial data from a set of non-adversaries. We conduct experiments to evaluate our algorithm, and the results indicate that it outperforms current algorithms.