{"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/transforming-vision-transformer-towards","title":"Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning","arxiv_id":"2501.06884","date":"2025-01-12","proceeding":null,"authors":["Hanwen Zhong","Jiaxin Chen","Yutong Zhang","Di Huang","Yunhong Wang"],"abstract":"Multi-Task Learning (MTL) for Vision Transformer aims at enhancing the model capability by tackling multiple tasks simultaneously. Most recent works have predominantly focused on designing Mixture-of-Experts (MoE) structures and in tegrating Low-Rank Adaptation (LoRA) to efficiently perform multi-task learning. However, their rigid combination hampers both the optimization of MoE and the ef fectiveness of reparameterization of LoRA, leading to sub-optimal performance and low inference speed. In this work, we propose a novel approach dubbed Efficient Multi-Task Learning (EMTAL) by transforming a pre-trained Vision Transformer into an efficient multi-task learner during training, and reparameterizing the learned structure for efficient inference. Specifically, we firstly develop the MoEfied LoRA structure, which decomposes the pre-trained Transformer into a low-rank MoE structure and employ LoRA to fine-tune the parameters. Subsequently, we take into account the intrinsic asynchronous nature of multi-task learning and devise a learning Quality Retaining (QR) optimization mechanism, by leveraging the historical high-quality class logits to prevent a well-trained task from performance degradation. Finally, we design a router fading strategy to integrate the learned parameters into the original Transformer, archiving efficient inference. Extensive experiments on public benchmarks demonstrate the superiority of our method, compared to the state-of-the-art multi-task learning approaches.","url_abs":"https://arxiv.org/abs/2501.06884v1","url_pdf":"https://arxiv.org/pdf/2501.06884v1.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":"transforming-vision-transformer-towards","repo_url":"https://github.com/yewen1486/emtal","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"moe","method_name":"MoE"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2501.06884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.06884"}},"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/Yewen1486/EMTAL","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yewen1486/emtal","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"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":"896b5eec245f1bab","entry":"init_ssf_scale_shift","repo":"yewen1486/emtal","repo_kind":"official","path":"models/vision_transformer.py","file_url":"https://github.com/yewen1486/emtal/blob/HEAD/models/vision_transformer.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":"896b5eec245f1bab"}},{"code_sha256_prefix":"88f4962784e09b88","entry":"param_groups_weight_decay","repo":"yewen1486/emtal","repo_kind":"official","path":"optim_factory.py","file_url":"https://github.com/yewen1486/emtal/blob/HEAD/optim_factory.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"88f4962784e09b88"}},{"code_sha256_prefix":"61e8364b7e9bcb70","entry":"ssf_ada","repo":"yewen1486/emtal","repo_kind":"official","path":"models/vision_transformer.py","file_url":"https://github.com/yewen1486/emtal/blob/HEAD/models/vision_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"61e8364b7e9bcb70"}},{"code_sha256_prefix":"efeb37d90ba28266","entry":"group_parameters","repo":"yewen1486/emtal","repo_kind":"official","path":"optim_factory.py","file_url":"https://github.com/yewen1486/emtal/blob/HEAD/optim_factory.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":"efeb37d90ba28266"}},{"code_sha256_prefix":"0332519996466b5a","entry":"group_with_matcher","repo":"yewen1486/emtal","repo_kind":"official","path":"optim_factory.py","file_url":"https://github.com/yewen1486/emtal/blob/HEAD/optim_factory.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":"0332519996466b5a"}},{"code_sha256_prefix":"3fdc6c4f02598de3","entry":"kl_divergence_loss","repo":"yewen1486/emtal","repo_kind":"official","path":"train_EMTAL.py","file_url":"https://github.com/yewen1486/emtal/blob/HEAD/train_EMTAL.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":"3fdc6c4f02598de3"}},{"code_sha256_prefix":"e2ee008f3497204c","entry":"validate","repo":"yewen1486/emtal","repo_kind":"official","path":"train_EMTAL.py","file_url":"https://github.com/yewen1486/emtal/blob/HEAD/train_EMTAL.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":"e2ee008f3497204c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}