{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/enabling-lightweight-fine-tuning-for-pre","title":"Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators","arxiv_id":"2106.02205","date":"2021-06-04","proceeding":"ACL 2021 5","authors":["Peiyu Liu","Ze-Feng Gao","Wayne Xin Zhao","Z. Y. Xie","Zhong-Yi Lu","Ji-Rong Wen"],"abstract":"This paper presents a novel pre-trained language models (PLM) compression approach based on the matrix product operator (short as MPO) from quantum many-body physics. It can decompose an original matrix into central tensors (containing the core information) and auxiliary tensors (with only a small proportion of parameters). With the decomposed MPO structure, we propose a novel fine-tuning strategy by only updating the parameters from the auxiliary tensors, and design an optimization algorithm for MPO-based approximation over stacked network architectures. Our approach can be applied to the original or the compressed PLMs in a general way, which derives a lighter network and significantly reduces the parameters to be fine-tuned. Extensive experiments have demonstrated the effectiveness of the proposed approach in model compression, especially the reduction in finetuning parameters (91% reduction on average).","url_abs":"https://arxiv.org/abs/2106.02205v1","url_pdf":"https://arxiv.org/pdf/2106.02205v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"enabling-lightweight-fine-tuning-for-pre","repo_url":"https://github.com/RUCAIBox/MPOP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"model-compression","task_name":"Model Compression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.02205","atlas_url":"https://app.syntology.ai/?focus=2106.02205","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}