新算法融合元学习与生成回放，提升流数据优化的适应速度和鲁棒性。
GeM-EA: A Generative and Meta-learning Enhanced Evolutionary Algorithm for Streaming Data-Driven Optimization
- 用元学习快速初始化代理模型，应对概念漂移。
- 生成回放机制利用历史知识加速搜索，提升收敛速度。
- 适合动态环境下的实时优化任务，如在线推荐系统。
流数据驱动优化（SDDO）问题广泛存在于数据持续到达且优化环境随时间演化的场景中。概念漂移导致非平稳优化景观，使传统方法因模型过时而失效。现有方法多依赖简单代理组合或直接注入解，可能在环境突变时引发负迁移。本文提出GeM-EA，一种融合生成式回放与元学习增强的进化算法，统一了元学习代理自适应与生成回放机制，实现高效进化搜索。检测到概念漂移后，双层元学习策略利用环境相关先验快速初始化代理模型，线性残差组件捕捉全局趋势；多岛进化策略通过生成回放复用历史知识，加速优化过程。在基准SDDO问题上的实验表明，相比当前最优方法，GeM-EA具备更快的适应速度与更强的鲁棒性。
原文摘要 · Abstract (English)
Streaming Data-Driven Optimization (SDDO) problems arise in many applications where data arrive continuously and the optimization environment evolves over time. Concept drift produces non-stationary landscapes, making optimization methods challenging due to outdated models. Existing approaches often rely on simple surrogate combinations or directly injecting solutions, which may cause negative transfer under sudden environmental changes. We propose GeM-EA, a Generative and Meta-learning Enhanced Evolutionary Algorithm for SDDO that unifies meta-learned surrogate adaptation with generative replay for effective evolutionary search. Upon detecting concept drift, a bi-level meta-learning strategy rapidly initializes the surrogate using environment-relevant priors, while a linear residual component captures global trends. A multi-island evolutionary strategy further leverages historical knowledge via generative replay to accelerate optimization. Experimental results on benchmark SDDO problems demonstrate that GeM-EA achieves faster adaptation and improved robustness compared with state-of-the-art methods.
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。