{"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/a-rigorous-study-of-the-deep-taylor","title":"A Rigorous Study Of The Deep Taylor Decomposition","arxiv_id":"2211.08425","date":"2022-11-14","proceeding":null,"authors":["Leon Sixt","Tim Landgraf"],"abstract":"Saliency methods attempt to explain deep neural networks by highlighting the most salient features of a sample. Some widely used methods are based on a theoretical framework called Deep Taylor Decomposition (DTD), which formalizes the recursive application of the Taylor Theorem to the network's layers. However, recent work has found these methods to be independent of the network's deeper layers and appear to respond only to lower-level image structure. Here, we investigate the DTD theory to better understand this perplexing behavior and found that the Deep Taylor Decomposition is equivalent to the basic gradient$\\times$input method when the Taylor root points (an important parameter of the algorithm chosen by the user) are locally constant. If the root points are locally input-dependent, then one can justify any explanation. In this case, the theory is under-constrained. In an empirical evaluation, we find that DTD roots do not lie in the same linear regions as the input - contrary to a fundamental assumption of the Taylor theorem. The theoretical foundations of DTD were cited as a source of reliability for the explanations. However, our findings urge caution in making such claims.","url_abs":"https://arxiv.org/abs/2211.08425v1","url_pdf":"https://arxiv.org/pdf/2211.08425v1.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":"a-rigorous-study-of-the-deep-taylor","repo_url":"https://github.com/berleon/a-rigorous-study-of-the-deep-taylor-decomposition","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.08425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.08425"}},"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/berleon/a-rigorous-study-of-the-deep-taylor-decomposition","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"42cadfab6b1810a9","entry":"equal_vmin_vmax","repo":"berleon/a-rigorous-study-of-the-deep-taylor-decomposition","repo_kind":"official","path":"lrp_relations/figures.py","file_url":"https://github.com/berleon/a-rigorous-study-of-the-deep-taylor-decomposition/blob/HEAD/lrp_relations/figures.py","link_basis":"harvester_set","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":"42cadfab6b1810a9"}},{"code_sha256_prefix":"d5bbeee432c42704","entry":"get_figure_size","repo":"berleon/a-rigorous-study-of-the-deep-taylor-decomposition","repo_kind":"official","path":"lrp_relations/figures.py","file_url":"https://github.com/berleon/a-rigorous-study-of-the-deep-taylor-decomposition/blob/HEAD/lrp_relations/figures.py","link_basis":"harvester_set","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":"d5bbeee432c42704"}},{"code_sha256_prefix":"8f32c21996b8aa23","entry":"grad_mask_for_logit","repo":"berleon/a-rigorous-study-of-the-deep-taylor-decomposition","repo_kind":"official","path":"lrp_relations/dtd.py","file_url":"https://github.com/berleon/a-rigorous-study-of-the-deep-taylor-decomposition/blob/HEAD/lrp_relations/dtd.py","link_basis":"harvester_set","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":"8f32c21996b8aa23"}},{"code_sha256_prefix":"f528cffc42b5a304","entry":"l2_norm_sq","repo":"berleon/a-rigorous-study-of-the-deep-taylor-decomposition","repo_kind":"official","path":"lrp_relations/gt_eval.py","file_url":"https://github.com/berleon/a-rigorous-study-of-the-deep-taylor-decomposition/blob/HEAD/lrp_relations/gt_eval.py","link_basis":"harvester_set","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":"f528cffc42b5a304"}},{"code_sha256_prefix":"94f7e84f2f0cadfe","entry":"relevance_mass","repo":"berleon/a-rigorous-study-of-the-deep-taylor-decomposition","repo_kind":"official","path":"lrp_relations/gt_eval.py","file_url":"https://github.com/berleon/a-rigorous-study-of-the-deep-taylor-decomposition/blob/HEAD/lrp_relations/gt_eval.py","link_basis":"harvester_set","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":"94f7e84f2f0cadfe"}},{"code_sha256_prefix":"e50644ed86b9ceb3","entry":"sample_interpolation","repo":"berleon/a-rigorous-study-of-the-deep-taylor-decomposition","repo_kind":"official","path":"lrp_relations/local_linear.py","file_url":"https://github.com/berleon/a-rigorous-study-of-the-deep-taylor-decomposition/blob/HEAD/lrp_relations/local_linear.py","link_basis":"harvester_set","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":"e50644ed86b9ceb3"}},{"code_sha256_prefix":"a121d4a195d1e997","entry":"sample_metropolis_hasting","repo":"berleon/a-rigorous-study-of-the-deep-taylor-decomposition","repo_kind":"official","path":"lrp_relations/local_linear.py","file_url":"https://github.com/berleon/a-rigorous-study-of-the-deep-taylor-decomposition/blob/HEAD/lrp_relations/local_linear.py","link_basis":"harvester_set","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":"a121d4a195d1e997"}},{"code_sha256_prefix":"30b546127d3d60cb","entry":"underscore_to_camelcase","repo":"berleon/a-rigorous-study-of-the-deep-taylor-decomposition","repo_kind":"official","path":"lrp_relations/figures.py","file_url":"https://github.com/berleon/a-rigorous-study-of-the-deep-taylor-decomposition/blob/HEAD/lrp_relations/figures.py","link_basis":"harvester_set","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":"30b546127d3d60cb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}