{"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/discriminability-transferability-trade-off-an","title":"Discriminability-Transferability Trade-Off: An Information-Theoretic Perspective","arxiv_id":"2203.03871","date":"2022-03-08","proceeding":null,"authors":["Quan Cui","Bingchen Zhao","Zhao-Min Chen","Borui Zhao","RenJie Song","Jiajun Liang","Boyan Zhou","Osamu Yoshie"],"abstract":"This work simultaneously considers the discriminability and transferability properties of deep representations in the typical supervised learning task, i.e., image classification. By a comprehensive temporal analysis, we observe a trade-off between these two properties. The discriminability keeps increasing with the training progressing while the transferability intensely diminishes in the later training period. From the perspective of information-bottleneck theory, we reveal that the incompatibility between discriminability and transferability is attributed to the over-compression of input information. More importantly, we investigate why and how the InfoNCE loss can alleviate the over-compression, and further present a learning framework, named contrastive temporal coding~(CTC), to counteract the over-compression and alleviate the incompatibility. Extensive experiments validate that CTC successfully mitigates the incompatibility, yielding discriminative and transferable representations. Noticeable improvements are achieved on the image classification task and challenging transfer learning tasks. We hope that this work will raise the significance of the transferability property in the conventional supervised learning setting. Code is available at https://github.com/DTennant/dt-tradeoff.","url_abs":"https://arxiv.org/abs/2203.03871v3","url_pdf":"https://arxiv.org/pdf/2203.03871v3.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":"discriminability-transferability-trade-off-an","repo_url":"https://github.com/dtennant/dt-tradeoff","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"infonce","method_name":"InfoNCE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2203.03871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.03871"}},"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/dtennant/dt-tradeoff","reach":null}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":6,"samples":[{"code_sha256_prefix":"0623387d3fc470ae","entry":"AliasMethod","repo":"dtennant/dt-tradeoff","repo_kind":"official","path":"ctc/criterion.py","file_url":"https://github.com/dtennant/dt-tradeoff/blob/HEAD/ctc/criterion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0623387d3fc470ae"}},{"code_sha256_prefix":"ac6ff5b3409890d5","entry":"ContrastLoss","repo":"dtennant/dt-tradeoff","repo_kind":"official","path":"ctc/criterion.py","file_url":"https://github.com/dtennant/dt-tradeoff/blob/HEAD/ctc/criterion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ac6ff5b3409890d5"}},{"code_sha256_prefix":"1a66230ccdff534e","entry":"ContrastMemory","repo":"dtennant/dt-tradeoff","repo_kind":"official","path":"ctc/criterion.py","file_url":"https://github.com/dtennant/dt-tradeoff/blob/HEAD/ctc/criterion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1a66230ccdff534e"}},{"code_sha256_prefix":"b6c6cecd56066877","entry":"Embed","repo":"dtennant/dt-tradeoff","repo_kind":"official","path":"ctc/criterion.py","file_url":"https://github.com/dtennant/dt-tradeoff/blob/HEAD/ctc/criterion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b6c6cecd56066877"}},{"code_sha256_prefix":"f863c8104c19474d","entry":"Normalize","repo":"dtennant/dt-tradeoff","repo_kind":"official","path":"ctc/criterion.py","file_url":"https://github.com/dtennant/dt-tradeoff/blob/HEAD/ctc/criterion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f863c8104c19474d"}},{"code_sha256_prefix":"47efee388b17abe8","entry":"ContrastiveLoss","repo":"dtennant/dt-tradeoff","repo_kind":"official","path":"ctc/criterion.py","file_url":"https://github.com/dtennant/dt-tradeoff/blob/HEAD/ctc/criterion.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":"47efee388b17abe8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}