{"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/compacter-efficient-low-rank-hypercomplex","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","arxiv_id":"2106.04647","date":"2021-06-08","proceeding":"NeurIPS 2021 12","authors":["Rabeeh Karimi Mahabadi","James Henderson","Sebastian Ruder"],"abstract":"Adapting large-scale pretrained language models to downstream tasks via fine-tuning is the standard method for achieving state-of-the-art performance on NLP benchmarks. However, fine-tuning all weights of models with millions or billions of parameters is sample-inefficient, unstable in low-resource settings, and wasteful as it requires storing a separate copy of the model for each task. Recent work has developed parameter-efficient fine-tuning methods, but these approaches either still require a relatively large number of parameters or underperform standard fine-tuning. In this work, we propose Compacter, a method for fine-tuning large-scale language models with a better trade-off between task performance and the number of trainable parameters than prior work. Compacter accomplishes this by building on top of ideas from adapters, low-rank optimization, and parameterized hypercomplex multiplication layers. Specifically, Compacter inserts task-specific weight matrices into a pretrained model's weights, which are computed efficiently as a sum of Kronecker products between shared \"slow\" weights and \"fast\" rank-one matrices defined per Compacter layer. By only training 0.047% of a pretrained model's parameters, Compacter performs on par with standard fine-tuning on GLUE and outperforms standard fine-tuning on SuperGLUE and low-resource settings. Our code is publicly available at~\\url{https://github.com/rabeehk/compacter}.","url_abs":"https://arxiv.org/abs/2106.04647v2","url_pdf":"https://arxiv.org/pdf/2106.04647v2.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":"compacter-efficient-low-rank-hypercomplex","repo_url":"https://github.com/rabeehk/compacter","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"compacter-efficient-low-rank-hypercomplex","repo_url":"https://github.com/cloneofsimo/lora","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.04647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04647"}},"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":"deterministic:regex_extraction","url":"https://github.com/rabeehk/compacter","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cloneofsimo/lora","reach":null}],"summary":{"ran_draft_wrong":4,"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":7,"samples":[{"code_sha256_prefix":"7ecc9e97effd20b6","entry":"glorot_normal","repo":"rabeehk/compacter","repo_kind":"official","path":"seq2seq/hypercomplex/layers.py","file_url":"https://github.com/rabeehk/compacter/blob/HEAD/seq2seq/hypercomplex/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7ecc9e97effd20b6"}},{"code_sha256_prefix":"b2ee26e229353a37","entry":"glorot_uniform","repo":"rabeehk/compacter","repo_kind":"official","path":"seq2seq/hypercomplex/layers.py","file_url":"https://github.com/rabeehk/compacter/blob/HEAD/seq2seq/hypercomplex/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b2ee26e229353a37"}},{"code_sha256_prefix":"5540414829f19945","entry":"kronecker_product","repo":"rabeehk/compacter","repo_kind":"official","path":"seq2seq/hypercomplex/layers.py","file_url":"https://github.com/rabeehk/compacter/blob/HEAD/seq2seq/hypercomplex/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5540414829f19945"}},{"code_sha256_prefix":"59e2991d3f405758","entry":"kronecker_product_einsum_batched","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"59e2991d3f405758"}},{"code_sha256_prefix":"44e48dfbdecee3da","entry":"run_command","repo":"rabeehk/compacter","repo_kind":"official","path":"seq2seq/run_seq2seq.py","file_url":"https://github.com/rabeehk/compacter/blob/HEAD/seq2seq/run_seq2seq.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"44e48dfbdecee3da"}},{"code_sha256_prefix":"7979cb8ef8d378cf","entry":"PHMLinear","repo":"rabeehk/compacter","repo_kind":"official","path":"seq2seq/hypercomplex/layers.py","file_url":"https://github.com/rabeehk/compacter/blob/HEAD/seq2seq/hypercomplex/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7979cb8ef8d378cf"}},{"code_sha256_prefix":"7dae3e67e6722206","entry":"matvec_product","repo":"rabeehk/compacter","repo_kind":"official","path":"seq2seq/hypercomplex/layers.py","file_url":"https://github.com/rabeehk/compacter/blob/HEAD/seq2seq/hypercomplex/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7dae3e67e6722206"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}