通信学报2026，Vol.47Issue(4)：67-79,13.DOI:10.11959/j.issn.1000-436x.2026062
基于组播时间扩展图的集合通信编排算法
Multicast time-expanded graph-based collective communication scheduling algorithm
摘要
Abstract
Collective communication latency has become a major performance bottleneck in large-scale distributed train-ing.To address the limitations of existing algorithms in terms of insufficient topology awareness and high computational complexity,a topology-aware collective communication scheduling algorithm based on multicast time-expanded graph was proposed.By constructing a multicast time-varying graph model,both network topology constraints and time-slot conflict constraints were explicitly captured.The collective communication scheduling problem was then transformed into a multicast path search problem on the time-varying graph,enabling joint optimization of routing and time slot plan-ning.Simulation results demonstrate that the proposed algorithm achieves near-optimal communication completion time while significantly reducing computational complexity,making it suitable for large-scale distributed training scenarios.关键词
集合通信/拓扑感知/时变图/组播调度/分布式训练Key words
collective communication/topology aware/time-varying graph/multicast scheduling/distributed training分类
信息技术与安全科学引用本文复制引用
刘飞,王鹏,麻涵,李烨,李红艳..基于组播时间扩展图的集合通信编排算法[J].通信学报,2026,47(4):67-79,13.基金项目
国家自然科学基金资助项目(No.62371374) The National Natural Science Foundation of China(No.62371374) （No.62371374）
