{"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/mtl-lora-low-rank-adaptation-for-multi-task","title":"MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning","arxiv_id":"2410.09437","date":"2024-10-12","proceeding":null,"authors":["Yaming Yang","Dilxat Muhtar","Yelong Shen","Yuefeng Zhan","Jianfeng Liu","Yujing Wang","Hao Sun","Denvy Deng","Feng Sun","Qi Zhang","Weizhu Chen","Yunhai Tong"],"abstract":"Parameter-efficient fine-tuning (PEFT) has been widely employed for domain adaptation, with LoRA being one of the most prominent methods due to its simplicity and effectiveness. However, in multi-task learning (MTL) scenarios, LoRA tends to obscure the distinction between tasks by projecting sparse high-dimensional features from different tasks into the same dense low-dimensional intrinsic space. This leads to task interference and suboptimal performance for LoRA and its variants. To tackle this challenge, we propose MTL-LoRA, which retains the advantages of low-rank adaptation while significantly enhancing MTL capabilities. MTL-LoRA augments LoRA by incorporating additional task-adaptive parameters that differentiate task-specific information and capture shared knowledge across various tasks within low-dimensional spaces. This approach enables pre-trained models to jointly adapt to different target domains with a limited number of trainable parameters. Comprehensive experimental results, including evaluations on public academic benchmarks for natural language understanding, commonsense reasoning, and image-text understanding, as well as real-world industrial text Ads relevance datasets, demonstrate that MTL-LoRA outperforms LoRA and its various variants with comparable or even fewer learnable parameters in MTL setting.","url_abs":"https://arxiv.org/abs/2410.09437v3","url_pdf":"https://arxiv.org/pdf/2410.09437v3.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":"mtl-lora-low-rank-adaptation-for-multi-task","repo_url":"https://github.com/pumpkin-co/mtl-lora","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2410.09437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09437"}},"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/pumpkin-co/mtl-lora","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_draft_wrong":2,"unverified":4},"by_repo_kind":{"official":{"samples":9,"ran":5,"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":"68e41c28a6dfe81d","entry":"collate_fn","repo":"pumpkin-co/mtl-lora","repo_kind":"official","path":"image_text_understanding/feature_extraction/refcocog_mattnet.py","file_url":"https://github.com/pumpkin-co/mtl-lora/blob/HEAD/image_text_understanding/feature_extraction/refcocog_mattnet.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":"68e41c28a6dfe81d"}},{"code_sha256_prefix":"dcba3394053b84cd","entry":"create_batch","repo":"pumpkin-co/mtl-lora","repo_kind":"official","path":"mlora_evaluate.py","file_url":"https://github.com/pumpkin-co/mtl-lora/blob/HEAD/mlora_evaluate.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":"dcba3394053b84cd"}},{"code_sha256_prefix":"56e674752db00649","entry":"generate_prompt","repo":"pumpkin-co/mtl-lora","repo_kind":"official","path":"lora_finetune.py","file_url":"https://github.com/pumpkin-co/mtl-lora/blob/HEAD/lora_finetune.py","link_basis":"harvester_set","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":"56e674752db00649"}},{"code_sha256_prefix":"1c6b8be890b6118a","entry":"generate_prompt","repo":"pumpkin-co/mtl-lora","repo_kind":"official","path":"lora_evaluate.py","file_url":"https://github.com/pumpkin-co/mtl-lora/blob/HEAD/lora_evaluate.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1c6b8be890b6118a"}},{"code_sha256_prefix":"660073ae6862ac6e","entry":"lora_state_dict","repo":"pumpkin-co/mtl-lora","repo_kind":"official","path":"image_text_understanding/VL-T5/src/lora/utils.py","file_url":"https://github.com/pumpkin-co/mtl-lora/blob/HEAD/image_text_understanding/VL-T5/src/lora/utils.py","link_basis":"harvester_set","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":"660073ae6862ac6e"}},{"code_sha256_prefix":"1d07463312991f52","entry":"load_data","repo":"pumpkin-co/mtl-lora","repo_kind":"official","path":"lora_evaluate.py","file_url":"https://github.com/pumpkin-co/mtl-lora/blob/HEAD/lora_evaluate.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":"1d07463312991f52"}},{"code_sha256_prefix":"9b2aa09fa1644193","entry":"main","repo":"pumpkin-co/mtl-lora","repo_kind":"official","path":"lora_evaluate.py","file_url":"https://github.com/pumpkin-co/mtl-lora/blob/HEAD/lora_evaluate.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":"9b2aa09fa1644193"}},{"code_sha256_prefix":"6cf4a819aa35986b","entry":"train","repo":"pumpkin-co/mtl-lora","repo_kind":"official","path":"lora_finetune.py","file_url":"https://github.com/pumpkin-co/mtl-lora/blob/HEAD/lora_finetune.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":"6cf4a819aa35986b"}},{"code_sha256_prefix":"823409f0ab13f67c","entry":"train","repo":"pumpkin-co/mtl-lora","repo_kind":"official","path":"lora_finetune_single.py","file_url":"https://github.com/pumpkin-co/mtl-lora/blob/HEAD/lora_finetune_single.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":"823409f0ab13f67c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}