{"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/transferring-inductive-biases-through","title":"Transferring Inductive Biases through Knowledge Distillation","arxiv_id":"2006.00555","date":"2020-05-31","proceeding":null,"authors":["Samira Abnar","Mostafa Dehghani","Willem Zuidema"],"abstract":"Having the right inductive biases can be crucial in many tasks or scenarios where data or computing resources are a limiting factor, or where training data is not perfectly representative of the conditions at test time. However, defining, designing and efficiently adapting inductive biases is not necessarily straightforward. In this paper, we explore the power of knowledge distillation for transferring the effect of inductive biases from one model to another. We consider families of models with different inductive biases, LSTMs vs. Transformers and CNNs vs. MLPs, in the context of tasks and scenarios where having the right inductive biases is critical. We study the effect of inductive biases on the solutions the models converge to and investigate how and to what extent the effect of inductive biases is transferred through knowledge distillation, in terms of not only performance but also different aspects of converged solutions.","url_abs":"https://arxiv.org/abs/2006.00555v3","url_pdf":"https://arxiv.org/pdf/2006.00555v3.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":"transferring-inductive-biases-through","repo_url":"https://github.com/samiraabnar/Reflect","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.00555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.00555"}},"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/samiraabnar/Reflect","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"ran":1,"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":"6220c13c591c68a7","entry":"shape_list","repo":"samiraabnar/Reflect","repo_kind":"official","path":"tf2_models/common_layers.py","file_url":"https://github.com/samiraabnar/Reflect/blob/HEAD/tf2_models/common_layers.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6220c13c591c68a7"}},{"code_sha256_prefix":"02c6d20363dfb076","entry":"distill_loss","repo":"samiraabnar/Reflect","repo_kind":"official","path":"tf2_models/metrics.py","file_url":"https://github.com/samiraabnar/Reflect/blob/HEAD/tf2_models/metrics.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":"02c6d20363dfb076"}},{"code_sha256_prefix":"47451fbef579f4fc","entry":"gelu","repo":"samiraabnar/Reflect","repo_kind":"official","path":"tf2_models/common_layers.py","file_url":"https://github.com/samiraabnar/Reflect/blob/HEAD/tf2_models/common_layers.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":"47451fbef579f4fc"}},{"code_sha256_prefix":"488a1d723fa95280","entry":"get_initializer","repo":"samiraabnar/Reflect","repo_kind":"official","path":"tf2_models/common_layers.py","file_url":"https://github.com/samiraabnar/Reflect/blob/HEAD/tf2_models/common_layers.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":"488a1d723fa95280"}},{"code_sha256_prefix":"0800e43230ecb35d","entry":"masked_sequence_loss","repo":"samiraabnar/Reflect","repo_kind":"official","path":"tf2_models/metrics.py","file_url":"https://github.com/samiraabnar/Reflect/blob/HEAD/tf2_models/metrics.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":"0800e43230ecb35d"}},{"code_sha256_prefix":"3686362b18aeccb8","entry":"max_out","repo":"samiraabnar/Reflect","repo_kind":"official","path":"tf2_models/cnn.py","file_url":"https://github.com/samiraabnar/Reflect/blob/HEAD/tf2_models/cnn.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":"3686362b18aeccb8"}},{"code_sha256_prefix":"7629a5fc4fbe87b4","entry":"sequence_distill_loss","repo":"samiraabnar/Reflect","repo_kind":"official","path":"tf2_models/metrics.py","file_url":"https://github.com/samiraabnar/Reflect/blob/HEAD/tf2_models/metrics.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":"7629a5fc4fbe87b4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}