Abstract
As an emerging paradigm considering data privacy and transmission efficiency, decentralized learning aims to acquire a global model using the training data distributed over many user devices. It is a challenging problem since link loss, partial device participation, and non-independent and identically distributed (non-iid) data distribution would all deteriorate the performance of decentralized learning algorithms. Existing work may restrict to linear models or show poor performance over non-iid data. Therefore, in this paper, we propose a decentralized learning scheme based on distributed parallel stochastic gradient descent (DPSGD) and graph neural network (GNN) to deal with the above challenges. Specifically, each user device participating in the learning task utilizes local training data to compute local stochastic gradients and updates its own local model. Then, each device utilizes the GNN model and exchanges the model parameters with its neighbors to reach the average of resultant global models. The iteration repeats until the algorithm converges. Extensive simulation results over both iid and non-iid data validate the algorithm’s convergence to near optimal results and robustness to both link loss and partial device participation.
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Decentralized Graph Neural Network for Privacy-Preserving Recommendation;Proceedings of the 32nd ACM International Conference on Information and Knowledge Management;2023-10-21
2. Prediction of Path Loss in Wireless Communication Networks based on Swarm Optimized Gradient Dual Layer Graph Neural Network;2023 7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC);2023-10-11