{"ID":2878023,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.18860","arxiv_id":"2508.18860","title":"C-Flat++: Towards a More Efficient and Powerful Framework for Continual Learning","abstract":"Balancing sensitivity to new tasks and stability for retaining past knowledge is crucial in continual learning (CL). Recently, sharpness-aware minimization has proven effective in transfer learning and has also been adopted in continual learning (CL) to improve memory retention and learning efficiency. However, relying on zeroth-order sharpness alone may favor sharper minima over flatter ones in certain settings, leading to less robust and potentially suboptimal solutions. In this paper, we propose \\textbf{C}ontinual \\textbf{Flat}ness (\\textbf{C-Flat}), a method that promotes flatter loss landscapes tailored for CL. C-Flat offers plug-and-play compatibility, enabling easy integration with minimal modifications to the code pipeline. Besides, we present a general framework that integrates C-Flat into all major CL paradigms and conduct comprehensive comparisons with loss-minima optimizers and flat-minima-based CL methods. Our results show that C-Flat consistently improves performance across a wide range of settings. In addition, we introduce C-Flat++, an efficient yet effective framework that leverages selective flatness-driven promotion, significantly reducing the update cost required by C-Flat. Extensive experiments across multiple CL methods, datasets, and scenarios demonstrate the effectiveness and efficiency of our proposed approaches. Code is available at https://github.com/WanNaa/C-Flat.","short_abstract":"Balancing sensitivity to new tasks and stability for retaining past knowledge is crucial in continual learning (CL). Recently, sharpness-aware minimization has proven effective in transfer learning and has also been adopted in continual learning (CL) to improve memory retention and learning efficiency. However, relying...","url_abs":"https://arxiv.org/abs/2508.18860","url_pdf":"https://arxiv.org/pdf/2508.18860v2","authors":"[\"Wei Li\",\"Hangjie Yuan\",\"Zixiang Zhao\",\"Yifan Zhu\",\"Aojun Lu\",\"Tao Feng\",\"Yanan Sun\"]","published":"2025-08-26T09:39:09Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":610442,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2878023,"paper_url":"https://arxiv.org/abs/2508.18860","paper_title":"C-Flat++: Towards a More Efficient and Powerful Framework for Continual Learning","repo_url":"https://github.com/WanNaa/C-Flat","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}