{"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/improving-explainability-of-disentangled","title":"Improving Explainability of Disentangled Representations using Multipath-Attribution Mappings","arxiv_id":"2306.09035","date":"2023-06-15","proceeding":null,"authors":["Lukas Klein","João B. S. Carvalho","Mennatallah El-Assady","Paolo Penna","Joachim M. Buhmann","Paul F. Jaeger"],"abstract":"Explainable AI aims to render model behavior understandable by humans, which can be seen as an intermediate step in extracting causal relations from correlative patterns. Due to the high risk of possible fatal decisions in image-based clinical diagnostics, it is necessary to integrate explainable AI into these safety-critical systems. Current explanatory methods typically assign attribution scores to pixel regions in the input image, indicating their importance for a model's decision. However, they fall short when explaining why a visual feature is used. We propose a framework that utilizes interpretable disentangled representations for downstream-task prediction. Through visualizing the disentangled representations, we enable experts to investigate possible causation effects by leveraging their domain knowledge. Additionally, we deploy a multi-path attribution mapping for enriching and validating explanations. We demonstrate the effectiveness of our approach on a synthetic benchmark suite and two medical datasets. We show that the framework not only acts as a catalyst for causal relation extraction but also enhances model robustness by enabling shortcut detection without the need for testing under distribution shifts.","url_abs":"https://arxiv.org/abs/2306.09035v1","url_pdf":"https://arxiv.org/pdf/2306.09035v1.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":"improving-explainability-of-disentangled","repo_url":"https://github.com/iml-dkfz/m-pax_lib","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2306.09035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.09035"}},"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/iml-dkfz/m-pax_lib","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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":"b2e93f279afbf340","entry":"arr_im_convert","repo":"iml-dkfz/m-pax_lib","repo_kind":"official","path":"src/evaluation/vis_helper.py","file_url":"https://github.com/iml-dkfz/m-pax_lib/blob/HEAD/src/evaluation/vis_helper.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b2e93f279afbf340"}},{"code_sha256_prefix":"ed74ccb76b1faf95","entry":"concatenate_pad","repo":"iml-dkfz/m-pax_lib","repo_kind":"official","path":"src/evaluation/vis_helper.py","file_url":"https://github.com/iml-dkfz/m-pax_lib/blob/HEAD/src/evaluation/vis_helper.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ed74ccb76b1faf95"}},{"code_sha256_prefix":"1fbb2f377c3568f1","entry":"main","repo":"iml-dkfz/m-pax_lib","repo_kind":"official","path":"run_eval.py","file_url":"https://github.com/iml-dkfz/m-pax_lib/blob/HEAD/run_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1fbb2f377c3568f1"}},{"code_sha256_prefix":"9f547bdc38fad1b9","entry":"main","repo":"iml-dkfz/m-pax_lib","repo_kind":"official","path":"run_head.py","file_url":"https://github.com/iml-dkfz/m-pax_lib/blob/HEAD/run_head.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9f547bdc38fad1b9"}},{"code_sha256_prefix":"00510feab827eb87","entry":"main","repo":"iml-dkfz/m-pax_lib","repo_kind":"official","path":"run_tcvae.py","file_url":"https://github.com/iml-dkfz/m-pax_lib/blob/HEAD/run_tcvae.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"00510feab827eb87"}},{"code_sha256_prefix":"7faac0f48cc9f483","entry":"make_grid_img","repo":"iml-dkfz/m-pax_lib","repo_kind":"official","path":"src/evaluation/vis_helper.py","file_url":"https://github.com/iml-dkfz/m-pax_lib/blob/HEAD/src/evaluation/vis_helper.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7faac0f48cc9f483"}},{"code_sha256_prefix":"c133dbaa8240dd1d","entry":"make_weights_for_balanced_classes","repo":"iml-dkfz/m-pax_lib","repo_kind":"official","path":"src/datamodules/isic_datamodule.py","file_url":"https://github.com/iml-dkfz/m-pax_lib/blob/HEAD/src/datamodules/isic_datamodule.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c133dbaa8240dd1d"}},{"code_sha256_prefix":"4a4666cfd3de39ba","entry":"make_weights_for_balanced_classes","repo":"iml-dkfz/m-pax_lib","repo_kind":"official","path":"src/datamodules/oct_datamodule.py","file_url":"https://github.com/iml-dkfz/m-pax_lib/blob/HEAD/src/datamodules/oct_datamodule.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4a4666cfd3de39ba"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}