{"ID":2885319,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.05521","arxiv_id":"2508.05521","title":"Optimal Brain Connection: Towards Efficient Structural Pruning","abstract":"Structural pruning has been widely studied for its effectiveness in compressing neural networks. However, existing methods often neglect the interconnections among parameters. To address this limitation, this paper proposes a structural pruning framework termed Optimal Brain Connection. First, we introduce the Jacobian Criterion, a first-order metric for evaluating the saliency of structural parameters. Unlike existing first-order methods that assess parameters in isolation, our criterion explicitly captures both intra-component interactions and inter-layer dependencies. Second, we propose the Equivalent Pruning mechanism, which utilizes autoencoders to retain the contributions of all original connection--including pruned ones--during fine-tuning. Experimental results demonstrate that the Jacobian Criterion outperforms several popular metrics in preserving model performance, while the Equivalent Pruning mechanism effectively mitigates performance degradation after fine-tuning. Code: https://github.com/ShaowuChen/Optimal_Brain_Connection","short_abstract":"Structural pruning has been widely studied for its effectiveness in compressing neural networks. However, existing methods often neglect the interconnections among parameters. To address this limitation, this paper proposes a structural pruning framework termed Optimal Brain Connection. First, we introduce the Jacobian...","url_abs":"https://arxiv.org/abs/2508.05521","url_pdf":"https://arxiv.org/pdf/2508.05521v1","authors":"[\"Shaowu Chen\",\"Wei Ma\",\"Binhua Huang\",\"Qingyuan Wang\",\"Guoxin Wang\",\"Weize Sun\",\"Lei Huang\",\"Deepu John\"]","published":"2025-08-07T15:51:05Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":611178,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2885319,"paper_url":"https://arxiv.org/abs/2508.05521","paper_title":"Optimal Brain Connection: Towards Efficient Structural Pruning","repo_url":"https://github.com/ShaowuChen/Optimal_Brain_Connection","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}