{"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/mtlora-a-low-rank-adaptation-approach-for","title":"MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning","arxiv_id":"2403.20320","date":"2024-03-29","proceeding":null,"authors":["Ahmed Agiza","Marina Neseem","Sherief Reda"],"abstract":"Adapting models pre-trained on large-scale datasets to a variety of downstream tasks is a common strategy in deep learning. Consequently, parameter-efficient fine-tuning methods have emerged as a promising way to adapt pre-trained models to different tasks while training only a minimal number of parameters. While most of these methods are designed for single-task adaptation, parameter-efficient training in Multi-Task Learning (MTL) architectures is still unexplored. In this paper, we introduce MTLoRA, a novel framework for parameter-efficient training of MTL models. MTLoRA employs Task-Agnostic and Task-Specific Low-Rank Adaptation modules, which effectively disentangle the parameter space in MTL fine-tuning, thereby enabling the model to adeptly handle both task specialization and interaction within MTL contexts. We applied MTLoRA to hierarchical-transformer-based MTL architectures, adapting them to multiple downstream dense prediction tasks. Our extensive experiments on the PASCAL dataset show that MTLoRA achieves higher accuracy on downstream tasks compared to fully fine-tuning the MTL model while reducing the number of trainable parameters by 3.6x. Furthermore, MTLoRA establishes a Pareto-optimal trade-off between the number of trainable parameters and the accuracy of the downstream tasks, outperforming current state-of-the-art parameter-efficient training methods in both accuracy and efficiency. Our code is publicly available.","url_abs":"https://arxiv.org/abs/2403.20320v1","url_pdf":"https://arxiv.org/pdf/2403.20320v1.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":"mtlora-a-low-rank-adaptation-approach-for","repo_url":"https://github.com/scale-lab/mtlora","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.20320","atlas_url":"https://app.syntology.ai/?focus=2403.20320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.20320"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/scale-lab/mtlora","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran":6,"ran_draft_wrong":2,"unverified":4},"by_repo_kind":{"official":{"samples":13,"ran":9,"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":"144d10b49baeb8a6","entry":"window_partition","repo":"scale-lab/mtlora","repo_kind":"official","path":"models/swin_transformer_mtlora.py","file_url":"https://github.com/scale-lab/mtlora/blob/HEAD/models/swin_transformer_mtlora.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"144d10b49baeb8a6"}},{"code_sha256_prefix":"016895042cc7e7ef","entry":"build_scheduler","repo":"scale-lab/mtlora","repo_kind":"official","path":"lr_scheduler.py","file_url":"https://github.com/scale-lab/mtlora/blob/HEAD/lr_scheduler.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":"016895042cc7e7ef"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"scale-lab/mtlora","repo_kind":"official","path":"models/seg_hrnet.py","file_url":"https://github.com/scale-lab/mtlora/blob/HEAD/models/seg_hrnet.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":"fac5364e2f53c6db"}},{"code_sha256_prefix":"299f2d40c6a8adc7","entry":"create_logger","repo":"scale-lab/mtlora","repo_kind":"official","path":"logger.py","file_url":"https://github.com/scale-lab/mtlora/blob/HEAD/logger.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":"299f2d40c6a8adc7"}},{"code_sha256_prefix":"80c0c9e218ee946c","entry":"get_loss","repo":"scale-lab/mtlora","repo_kind":"official","path":"mtl_loss_schemes.py","file_url":"https://github.com/scale-lab/mtlora/blob/HEAD/mtl_loss_schemes.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":"80c0c9e218ee946c"}},{"code_sha256_prefix":"7c89e5e716dec3fc","entry":"lora_filter","repo":"scale-lab/mtlora","repo_kind":"official","path":"models/lora.py","file_url":"https://github.com/scale-lab/mtlora/blob/HEAD/models/lora.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":"7c89e5e716dec3fc"}},{"code_sha256_prefix":"9f7d1c2d347cb4aa","entry":"map_old_state_dict_weights","repo":"scale-lab/mtlora","repo_kind":"official","path":"models/lora.py","file_url":"https://github.com/scale-lab/mtlora/blob/HEAD/models/lora.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":"9f7d1c2d347cb4aa"}},{"code_sha256_prefix":"368118c367337eb7","entry":"resize","repo":"scale-lab/mtlora","repo_kind":"official","path":"models/segformer.py","file_url":"https://github.com/scale-lab/mtlora/blob/HEAD/models/segformer.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":"368118c367337eb7"}},{"code_sha256_prefix":"61bf152e6a42a184","entry":"window_reverse","repo":"scale-lab/mtlora","repo_kind":"official","path":"models/swin_transformer_mtlora.py","file_url":"https://github.com/scale-lab/mtlora/blob/HEAD/models/swin_transformer_mtlora.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"61bf152e6a42a184"}},{"code_sha256_prefix":"7d5cbe94b33d3a17","entry":"build_model","repo":"scale-lab/mtlora","repo_kind":"official","path":"models/build.py","file_url":"https://github.com/scale-lab/mtlora/blob/HEAD/models/build.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":"7d5cbe94b33d3a17"}},{"code_sha256_prefix":"d209ed6ef5c01da9","entry":"build_mtl_model","repo":"scale-lab/mtlora","repo_kind":"official","path":"models/build.py","file_url":"https://github.com/scale-lab/mtlora/blob/HEAD/models/build.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":"d209ed6ef5c01da9"}},{"code_sha256_prefix":"f3788eeccc68b1f0","entry":"mark_only_lora_as_trainable","repo":"scale-lab/mtlora","repo_kind":"official","path":"models/lora.py","file_url":"https://github.com/scale-lab/mtlora/blob/HEAD/models/lora.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":"f3788eeccc68b1f0"}},{"code_sha256_prefix":"5ebb5fe1837669a8","entry":"resize","repo":"scale-lab/mtlora","repo_kind":"official","path":"models/base_decode_head.py","file_url":"https://github.com/scale-lab/mtlora/blob/HEAD/models/base_decode_head.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":"5ebb5fe1837669a8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}