提出可在线更新的分布式图神经网络训练方法，提升网络系统智能化效率。
Fully Distributed Online Training of Graph Neural Networks in Networked Systems
- 采用完全分布式在线训练，每批数据仅增加L轮通信开销
- 在无线网络任务中实现监督、无监督与强化学习的有效训练
- 适合需实时响应的大型网络系统，如电网和交通网
图神经网络（GNN）是构建大规模网络化系统（如无线网络、电网、交通网）中可扩展去中心化人工智能的强大工具。当前大多数网络系统中的GNN遵循‘集中训练、分布式执行’范式，限制了其适应性并延缓开发周期。本文首次提出一种通信高效的全分布式在线训练方法，用于大规模网络系统的GNN。对于包含B个样本的迷你批次，训练一个L层GNN仅额外增加L轮消息传递，消息尺寸翻倍，相比推理所需的LB轮通信开销极低。通过在基于图的节点回归、电力分配及无线网络链路调度任务中的数值实验，验证了该方法在监督、无监督和强化学习范式下的有效性。
原文摘要 · Abstract (English)
Graph neural networks (GNNs) are powerful tools for developing scalable, decentralized artificial intelligence in large-scale networked systems, such as wireless networks, power grids, and transportation networks. Currently, GNNs in networked systems mostly follow a paradigm of `centralized training, distributed execution', which limits their adaptability and slows down their development cycles. In this work, we fill this gap for the first time by developing a communication-efficient, fully distributed online training approach for GNNs applied to large networked systems. For a mini-batch with $B$ samples, our approach of training an $L$-layer GNN only adds $L$ rounds of message passing to the $LB$ rounds required by GNN inference, with doubled message sizes. Through numerical experiments in graph-based node regression, power allocation, and link scheduling in wireless networks, we demonstrate the effectiveness of our approach in training GNNs under supervised, unsupervised, and reinforcement learning paradigms.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。