首个针对联邦时序预测遗忘问题的基准测试，验证多种缓解方法效果。
Benchmarking Catastrophic Forgetting Mitigation Methods in Federated Time Series Forecasting
- 构建联邦时序预测下的遗忘问题评估框架
- 在12个客户端的空气质量数据上对比多种缓解方法性能
- 适合研究持续学习与边缘智能的开发者和研究人员
灾难性遗忘（CF）是持续学习（CL）中的长期挑战，尤其在非独立同分布的时序数据联邦学习（FL）环境中更为突出。现有研究多聚焦于视觉领域的分类任务，而物联网与边缘应用中常见的回归型预测场景仍缺乏深入探索。本文首次提出面向联邦持续时序预测中灾难性遗忘的基准测试框架。基于12个分布式客户端的北京多站点空气质量数据集，系统评估了回放、弹性权重固化、无遗忘学习及突触智能等多种遗忘缓解策略。主要贡献包括：(i) 构建时序联邦学习中灾难性遗忘的新基准；(ii) 对主流方法进行综合对比分析；(iii) 开源可复现的实现框架。本工作为推进联邦时序预测中的持续学习提供了关键工具与洞见。
原文摘要 · Abstract (English)
Catastrophic forgetting (CF) poses a persistent challenge in continual learning (CL), especially within federated learning (FL) environments characterized by non-i.i.d. time series data. While existing research has largely focused on classification tasks in vision domains, the regression-based forecasting setting prevalent in IoT and edge applications remains underexplored. In this paper, we present the first benchmarking framework tailored to investigate CF in federated continual time series forecasting. Using the Beijing Multi-site Air Quality dataset across 12 decentralized clients, we systematically evaluate several CF mitigation strategies, including Replay, Elastic Weight Consolidation, Learning without Forgetting, and Synaptic Intelligence. Key contributions include: (i) introducing a new benchmark for CF in time series FL, (ii) conducting a comprehensive comparative analysis of state-of-the-art methods, and (iii) releasing a reproducible open-source framework. This work provides essential tools and insights for advancing continual learning in federated time-series forecasting systems.
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。