GeM-EA: A Generative and Meta-learning Enhanced Evolutionary Algorithm for Streaming Data-Driven Optimization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911591945994240 |
|---|---|
| author | Wu, Yue Zhong, Yuan-Ting Ma, Ze-Yuan Gong, Yue-Jiao |
| author_facet | Wu, Yue Zhong, Yuan-Ting Ma, Ze-Yuan Gong, Yue-Jiao |
| contents | 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 Concept drift produces non-stationary landscapes, making optimization methods challenging due to outdated models.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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12336 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GeM-EA: A Generative and Meta-learning Enhanced Evolutionary Algorithm for Streaming Data-Driven Optimization Wu, Yue Zhong, Yuan-Ting Ma, Ze-Yuan Gong, Yue-Jiao Neural and Evolutionary Computing Artificial Intelligence 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 Concept drift produces non-stationary landscapes, making optimization methods challenging due to outdated models.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. |
| title | GeM-EA: A Generative and Meta-learning Enhanced Evolutionary Algorithm for Streaming Data-Driven Optimization |
| topic | Neural and Evolutionary Computing Artificial Intelligence |
| url | https://arxiv.org/abs/2604.12336 |