{"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/parameter-efficient-sparsity-for-large","title":"Parameter-Efficient Sparsity for Large Language Models Fine-Tuning","arxiv_id":"2205.11005","date":"2022-05-23","proceeding":null,"authors":["Yuchao Li","Fuli Luo","Chuanqi Tan","Mengdi Wang","Songfang Huang","Shen Li","Junjie Bai"],"abstract":"With the dramatically increased number of parameters in language models, sparsity methods have received ever-increasing research focus to compress and accelerate the models. While most research focuses on how to accurately retain appropriate weights while maintaining the performance of the compressed model, there are challenges in the computational overhead and memory footprint of sparse training when compressing large-scale language models. To address this problem, we propose a Parameter-efficient Sparse Training (PST) method to reduce the number of trainable parameters during sparse-aware training in downstream tasks. Specifically, we first combine the data-free and data-driven criteria to efficiently and accurately measure the importance of weights. Then we investigate the intrinsic redundancy of data-driven weight importance and derive two obvious characteristics i.e., low-rankness and structuredness. Based on that, two groups of small matrices are introduced to compute the data-driven importance of weights, instead of using the original large importance score matrix, which therefore makes the sparse training resource-efficient and parameter-efficient. Experiments with diverse networks (i.e., BERT, RoBERTa and GPT-2) on dozens of datasets demonstrate PST performs on par or better than previous sparsity methods, despite only training a small number of parameters. For instance, compared with previous sparsity methods, our PST only requires 1.5% trainable parameters to achieve comparable performance on BERT.","url_abs":"https://arxiv.org/abs/2205.11005v1","url_pdf":"https://arxiv.org/pdf/2205.11005v1.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":"parameter-efficient-sparsity-for-large","repo_url":"https://github.com/alibaba/AliceMind","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"parameter-efficient-sparsity-for-large","repo_url":"https://github.com/yuchaoli/pst","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"tasks":[],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roberta","method_name":"RoBERTa"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.11005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11005"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alibaba/AliceMind","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yuchaoli/pst","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2c80e67eccf444c4","entry":"SparseBinarizer","repo":"alibaba/AliceMind","repo_kind":"official","path":"S4/PST/pst/sparse.py","file_url":"https://github.com/alibaba/AliceMind/blob/HEAD/S4/PST/pst/sparse.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2c80e67eccf444c4"}},{"code_sha256_prefix":"34ea0fcf1763a408","entry":"SparseLinear","repo":"alibaba/AliceMind","repo_kind":"official","path":"S4/PST/pst/sparse.py","file_url":"https://github.com/alibaba/AliceMind/blob/HEAD/S4/PST/pst/sparse.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"34ea0fcf1763a408"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}