{"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-kernel-transfer-in-gaussian-processes","title":"Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels","arxiv_id":"1910.05199","date":"2019-10-11","proceeding":"NeurIPS 2020 12","authors":["Massimiliano Patacchiola","Jack Turner","Elliot J. Crowley","Michael O'Boyle","Amos Storkey"],"abstract":"Recently, different machine learning methods have been introduced to tackle the challenging few-shot learning scenario that is, learning from a small labeled dataset related to a specific task. Common approaches have taken the form of meta-learning: learning to learn on the new problem given the old. Following the recognition that meta-learning is implementing learning in a multi-level model, we present a Bayesian treatment for the meta-learning inner loop through the use of deep kernels. As a result we can learn a kernel that transfers to new tasks; we call this Deep Kernel Transfer (DKT). This approach has many advantages: is straightforward to implement as a single optimizer, provides uncertainty quantification, and does not require estimation of task-specific parameters. We empirically demonstrate that DKT outperforms several state-of-the-art algorithms in few-shot classification, and is the state of the art for cross-domain adaptation and regression. We conclude that complex meta-learning routines can be replaced by a simpler Bayesian model without loss of accuracy.","url_abs":"https://arxiv.org/abs/1910.05199v4","url_pdf":"https://arxiv.org/pdf/1910.05199v4.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-kernel-transfer-in-gaussian-processes","repo_url":"https://github.com/BayesWatch/deep-kernel-transfer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-kernel-transfer-in-gaussian-processes","repo_url":"https://github.com/hhl60492/deep-kernel-transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-kernel-transfer-in-gaussian-processes","repo_url":"https://github.com/keanson/revisit-logistic-softmax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5-1","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way 1-shot","model":"DKT + BNCosSim","rank_in_archive_order":27,"of":36,"metrics":{"Accuracy":"72.27"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way 5-shot","model":"DKT + BNCosSim","rank_in_archive_order":24,"of":32,"metrics":{"Accuracy":"85.64"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-5","task":"Few-Shot Image Classification","dataset":"Mini-ImageNet-CUB 5-way (1-shot)","model":"DKT + CosSim","rank_in_archive_order":8,"of":12,"metrics":{"Accuracy":"40.22"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-6","task":"Few-Shot Image Classification","dataset":"Mini-ImageNet-CUB 5-way (5-shot)","model":"DKT + BNCosSim","rank_in_archive_order":8,"of":8,"metrics":{"Accuracy":"56.40"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-2","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (1-shot)","model":"DKT + BNCosSim","rank_in_archive_order":64,"of":105,"metrics":{"Accuracy":"62.96"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-3","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (5-shot)","model":"DKT + BNCosSim","rank_in_archive_order":92,"of":95,"metrics":{"Accuracy":"64.0"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot","task":"Few-Shot Image Classification","dataset":"OMNIGLOT-EMNIST 5-way (1-shot)","model":"DKT + BNCosSim","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"75.40"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-2","task":"Few-Shot Image Classification","dataset":"OMNIGLOT-EMNIST 5-way (5-shot)","model":"DKT + BNCosSim","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"90.3"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1910.05199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.05199"}},"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/keanson/revisit-logistic-softmax","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BayesWatch/deep-kernel-transfer","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hhl60492/deep-kernel-transfer","reach":{"status":"ok"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"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":1,"samples":[{"code_sha256_prefix":"a76efa59968132d5","entry":"psd_safe_cholesky","repo":"keanson/revisit-logistic-softmax","repo_kind":"listed","path":"methods/CDKT.py","file_url":"https://github.com/keanson/revisit-logistic-softmax/blob/HEAD/methods/CDKT.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":"a76efa59968132d5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}