{"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/self-supervised-generalisation-with-meta","title":"Self-Supervised Generalisation with Meta Auxiliary Learning","arxiv_id":"1901.08933","date":"2019-01-25","proceeding":"NeurIPS 2019 12","authors":["Shikun Liu","Andrew J. Davison","Edward Johns"],"abstract":"Learning with auxiliary tasks can improve the ability of a primary task to generalise. However, this comes at the cost of manually labelling auxiliary data. We propose a new method which automatically learns appropriate labels for an auxiliary task, such that any supervised learning task can be improved without requiring access to any further data. The approach is to train two neural networks: a label-generation network to predict the auxiliary labels, and a multi-task network to train the primary task alongside the auxiliary task. The loss for the label-generation network incorporates the loss of the multi-task network, and so this interaction between the two networks can be seen as a form of meta learning with a double gradient. We show that our proposed method, Meta AuXiliary Learning (MAXL), outperforms single-task learning on 7 image datasets, without requiring any additional data. We also show that MAXL outperforms several other baselines for generating auxiliary labels, and is even competitive when compared with human-defined auxiliary labels. The self-supervised nature of our method leads to a promising new direction towards automated generalisation. Source code can be found at https://github.com/lorenmt/maxl.","url_abs":"https://arxiv.org/abs/1901.08933v3","url_pdf":"https://arxiv.org/pdf/1901.08933v3.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":"self-supervised-generalisation-with-meta","repo_url":"https://github.com/lorenmt/maxl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"self-supervised-generalisation-with-meta","repo_url":"https://github.com/COMP6248-Reproducability-Challenge/COMP6248-Self-Supervised-Generalisation-with-Meta-Auxiliary-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"self-supervised-generalisation-with-meta","repo_url":"https://github.com/generation21/generation6011","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"self-supervised-generalisation-with-meta","repo_url":"https://github.com/sjn3303123/DL_Reproducibility","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"auxiliary-learning","task_name":"Auxiliary Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.08933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08933"}},"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/lorenmt/maxl","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/COMP6248-Reproducability-Challenge/COMP6248-Self-Supervised-Generalisation-with-Meta-Auxiliary-Learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/generation21/generation6011","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sjn3303123/DL_Reproducibility","reach":{"status":"ok"}}],"summary":{"ran_honours":2,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"b7e2184b1c0c0f17","entry":"ClassGenerator","repo":"COMP6248-Reproducability-Challenge/COMP6248-Self-Supervised-Generalisation-with-Meta-Auxiliary-Learning","repo_kind":"listed","path":"SimpleCNN/MNIST_MAXL.py","file_url":"https://github.com/COMP6248-Reproducability-Challenge/COMP6248-Self-Supervised-Generalisation-with-Meta-Auxiliary-Learning/blob/HEAD/SimpleCNN/MNIST_MAXL.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":"b7e2184b1c0c0f17"}},{"code_sha256_prefix":"1c9c9b3dc41c608e","entry":"ClassGenerator","repo":"COMP6248-Reproducability-Challenge/COMP6248-Self-Supervised-Generalisation-with-Meta-Auxiliary-Learning","repo_kind":"listed","path":"ResNet/model_ResNet_maxl_pri3.py","file_url":"https://github.com/COMP6248-Reproducability-Challenge/COMP6248-Self-Supervised-Generalisation-with-Meta-Auxiliary-Learning/blob/HEAD/ResNet/model_ResNet_maxl_pri3.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":"1c9c9b3dc41c608e"}},{"code_sha256_prefix":"ba64bb38b617cb31","entry":"ResNet32","repo":"COMP6248-Reproducability-Challenge/COMP6248-Self-Supervised-Generalisation-with-Meta-Auxiliary-Learning","repo_kind":"listed","path":"ResNet/model_ResNet_maxl_pri3.py","file_url":"https://github.com/COMP6248-Reproducability-Challenge/COMP6248-Self-Supervised-Generalisation-with-Meta-Auxiliary-Learning/blob/HEAD/ResNet/model_ResNet_maxl_pri3.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":"ba64bb38b617cb31"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}