发表机构
School of Information and Communication Engineering, Beijing University of Posts and Telecommunications (BUPT); Beijing Information Science and Technology University（北京邮电大学信息与通信工程学院; 北京信息科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对异构多任务语义通信中DFL的负迁移与OCB问题，提出个性化DSC框架，经NYU-v2等数据集验证，其最优聚合深度下性能优于多种基准方法。
AI 中文摘要
分布式语义通信（DSC）网络中的协作训练通常依赖去中心化联邦学习（DFL）。然而，将与拓扑无关的聚合应用于异构多任务环境会产生一个根本瓶颈：它会导致负迁移和过度共识偏差（OCB）。本文提出一种个性化DSC框架，可切断这种跨任务干扰。在节点层面，一种策略驱动的多路径路由机制将任务特定特征与共享表示分离，以保留局部保真度；在整个网络中，我们部署了一种“通信即聚合”协议，利用任务亲和性校准列随机共识矩阵，这限制系统仅吸收互补知识，同时主动阻止不匹配的参数更新。为界定收敛性，我们推导了统一的李雅普诺夫漂移分析，揭示了严格的U型权衡：更深的拓扑混合会降低方差，但会放大结构性OCB；解决该张力可得到最优聚合深度的闭式表达式。我们在NYU-v2数据集上评估所提框架，结果显示在聚合不足与过度拓扑混合之间存在明显权衡；在分析推导的最优聚合深度下，我们的方法较无聚合基准实现了4.77%的全局相对提升，且优于去中心化FedAvg、FedAMP及启发式最大聚合方法。我们还在Taskonomy数据集和不完善无线链路上评估该框架，以考察网络规模变化与无线链路可靠性的影响。
英文摘要
Collaborative training in distributed semantic communication (DSC) networks typically relies on decentralized federated learning (DFL). However, pushing topology-agnostic aggregation into heterogeneous, multi-task environments creates a fundamental bottleneck: it drives negative transfer and overconsensus bias (OCB). This paper introduces a personalized DSC framework that cuts off this cross-task interference. At the node level, a policy-driven multi-path routing mechanism separates task-specific features from shared representations to preserve local fidelity. Across the network, we deploy a "communicationwhile- aggregation" protocol. It calibrates a column-stochastic consensus matrix using task affinities. This limits the system to absorbing complementary knowledge while actively blocking mismatched parameter updates. To bound the convergence, we derive a unified Lyapunov drift analysis. We reveal a strict Ushaped trade-off: deeper topological mixing reduces variance but amplifies structural OCB. Resolving this tension yields a closed-form expression for the optimal aggregation depth. We evaluate the proposed framework on NYU-v2, where the results reveal a clear trade-off between insufficient aggregation and excessive topological mixing. At the analytically derived optimal aggregation depth, our method achieves a 4.77% global relative improvement over the no-aggregation baseline and outperforms decentralized FedAvg, FedAMP, and heuristic max aggregation. We further evaluate the framework on Taskonomy and imperfect wireless links to examine the effects of network-size variation and wireless-link reliability.
Comments17 pages, 9 figures, Accepted by IEEE Transactions on Communications
