{"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/make-lora-great-again-boosting-lora-with","title":"Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment","arxiv_id":"2502.16894","date":"2025-02-24","proceeding":null,"authors":["Chenghao Fan","Zhenyi Lu","Sichen Liu","Chengfeng Gu","Xiaoye Qu","Wei Wei","Yu Cheng"],"abstract":"While Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning for Large Language Models (LLMs), its performance often falls short of Full Fine-Tuning (Full FT). Current methods optimize LoRA by initializing with static singular value decomposition (SVD) subsets, leading to suboptimal leveraging of pre-trained knowledge. Another path for improving LoRA is incorporating a Mixture-of-Experts (MoE) architecture. However, weight misalignment and complex gradient dynamics make it challenging to adopt SVD prior to the LoRA MoE architecture. To mitigate these issues, we propose \\underline{G}reat L\\underline{o}R\\underline{A} Mixture-of-Exper\\underline{t} (GOAT), a framework that (1) adaptively integrates relevant priors using an SVD-structured MoE, and (2) aligns optimization with full fine-tuned MoE by deriving a theoretical scaling factor. We demonstrate that proper scaling, without modifying the architecture or training algorithms, boosts LoRA MoE's efficiency and performance. Experiments across 25 datasets, including natural language understanding, commonsense reasoning, image classification, and natural language generation, demonstrate GOAT's state-of-the-art performance, closing the gap with Full FT.","url_abs":"https://arxiv.org/abs/2502.16894v3","url_pdf":"https://arxiv.org/pdf/2502.16894v3.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":"make-lora-great-again-boosting-lora-with","repo_url":"https://github.com/facico/goat-peft","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"adopt","method_name":"ADOPT"},{"method_slug":"moe","method_name":"MoE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.16894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.16894"}},"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/facico/goat-peft","reach":null}],"summary":{"ran":3,"ran_draft_wrong":3,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"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":"f6281dca802f5478","entry":"GOATExpert","repo":"facico/goat-peft","repo_kind":"official","path":"goat/peta/src/goat/layer.py","file_url":"https://github.com/facico/goat-peft/blob/HEAD/goat/peta/src/goat/layer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6281dca802f5478"}},{"code_sha256_prefix":"b114d1cbcd1d211b","entry":"GOATLayer","repo":"facico/goat-peft","repo_kind":"official","path":"goat/peta/src/goat/layer.py","file_url":"https://github.com/facico/goat-peft/blob/HEAD/goat/peta/src/goat/layer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b114d1cbcd1d211b"}},{"code_sha256_prefix":"ee58e5aa29c6bc1a","entry":"TopKGOATLayer","repo":"facico/goat-peft","repo_kind":"official","path":"goat/peta/src/goat/layer.py","file_url":"https://github.com/facico/goat-peft/blob/HEAD/goat/peta/src/goat/layer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ee58e5aa29c6bc1a"}},{"code_sha256_prefix":"9a79ef50064b77e4","entry":"collate_fn","repo":"facico/goat-peft","repo_kind":"official","path":"goat/train_vit.py","file_url":"https://github.com/facico/goat-peft/blob/HEAD/goat/train_vit.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9a79ef50064b77e4"}},{"code_sha256_prefix":"7450a473b4f17f71","entry":"split_dataset","repo":"facico/goat-peft","repo_kind":"official","path":"goat/train_nlg.py","file_url":"https://github.com/facico/goat-peft/blob/HEAD/goat/train_nlg.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7450a473b4f17f71"}},{"code_sha256_prefix":"7d02e789de7329ec","entry":"split_dataset","repo":"facico/goat-peft","repo_kind":"official","path":"goat/train_vit.py","file_url":"https://github.com/facico/goat-peft/blob/HEAD/goat/train_vit.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d02e789de7329ec"}},{"code_sha256_prefix":"5075efb5ce5f9c08","entry":"gather_from_all_processes","repo":"facico/goat-peft","repo_kind":"official","path":"goat/train_nlg.py","file_url":"https://github.com/facico/goat-peft/blob/HEAD/goat/train_nlg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5075efb5ce5f9c08"}},{"code_sha256_prefix":"e76c4ac7377a13ee","entry":"gather_from_all_processes","repo":"facico/goat-peft","repo_kind":"official","path":"goat/train_vit.py","file_url":"https://github.com/facico/goat-peft/blob/HEAD/goat/train_vit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e76c4ac7377a13ee"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}