{"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/deep-multi-task-representation-learning-a","title":"Deep Multi-task Representation Learning: A Tensor Factorisation Approach","arxiv_id":"1605.06391","date":"2016-05-20","proceeding":null,"authors":["Yongxin Yang","Timothy Hospedales"],"abstract":"Most contemporary multi-task learning methods assume linear models. This\nsetting is considered shallow in the era of deep learning. In this paper, we\npresent a new deep multi-task representation learning framework that learns\ncross-task sharing structure at every layer in a deep network. Our approach is\nbased on generalising the matrix factorisation techniques explicitly or\nimplicitly used by many conventional MTL algorithms to tensor factorisation, to\nrealise automatic learning of end-to-end knowledge sharing in deep networks.\nThis is in contrast to existing deep learning approaches that need a\nuser-defined multi-task sharing strategy. Our approach applies to both\nhomogeneous and heterogeneous MTL. Experiments demonstrate the efficacy of our\ndeep multi-task representation learning in terms of both higher accuracy and\nfewer design choices.","url_abs":"http://arxiv.org/abs/1605.06391v2","url_pdf":"http://arxiv.org/pdf/1605.06391v2.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":"deep-multi-task-representation-learning-a","repo_url":"https://github.com/wOOL/DMTRL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-multi-task-representation-learning-a","repo_url":"https://github.com/safooray/tensor_factorization_mtl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Unlicense"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1605.06391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.06391"}},"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/safooray/tensor_factorization_mtl","reach":{"status":"ok","spdx":"Unlicense"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wOOL/DMTRL","reach":null}],"summary":{"ran_fixture":3},"by_repo_kind":{"official":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"8e5a74b622c1284a","entry":"my_svd","repo":"wOOL/DMTRL","repo_kind":"official","path":"tensor_toolbox_yyang.py","file_url":"https://github.com/wOOL/DMTRL/blob/HEAD/tensor_toolbox_yyang.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Unlicense","inline_ok":true,"mcp_get_code":{"code_sha256":"8e5a74b622c1284a"}},{"code_sha256_prefix":"f75c02764d883013","entry":"t_dot","repo":"wOOL/DMTRL","repo_kind":"official","path":"tensor_toolbox_yyang.py","file_url":"https://github.com/wOOL/DMTRL/blob/HEAD/tensor_toolbox_yyang.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Unlicense","inline_ok":true,"mcp_get_code":{"code_sha256":"f75c02764d883013"}},{"code_sha256_prefix":"b87a4f57f2656a22","entry":"t_unfold","repo":"wOOL/DMTRL","repo_kind":"official","path":"tensor_toolbox_yyang.py","file_url":"https://github.com/wOOL/DMTRL/blob/HEAD/tensor_toolbox_yyang.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Unlicense","inline_ok":true,"mcp_get_code":{"code_sha256":"b87a4f57f2656a22"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}