{"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/bim-towards-quantitative-evaluation-of","title":"Benchmarking Attribution Methods with Relative Feature Importance","arxiv_id":"1907.09701","date":"2019-07-23","proceeding":null,"authors":["Mengjiao Yang","Been Kim"],"abstract":"Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative evaluation of feature attribution methods remains difficult due to the lack of ground truth: we do not know which input features are in fact important to a model. In this work, we propose a framework for Benchmarking Attribution Methods (BAM) with a priori knowledge of relative feature importance. BAM includes 1) a carefully crafted dataset and models trained with known relative feature importance and 2) three complementary metrics to quantitatively evaluate attribution methods by comparing feature attributions between pairs of models and pairs of inputs. Our evaluation on several widely-used attribution methods suggests that certain methods are more likely to produce false positive explanations---features that are incorrectly attributed as more important to model prediction. We open source our dataset, models, and metrics.","url_abs":"https://arxiv.org/abs/1907.09701v2","url_pdf":"https://arxiv.org/pdf/1907.09701v2.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":"bim-towards-quantitative-evaluation-of","repo_url":"https://github.com/google-research-datasets/bim","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"bim-towards-quantitative-evaluation-of","repo_url":"https://github.com/google-research-datasets/bam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"feature-importance","task_name":"Feature Importance"}],"methods":[{"method_slug":"bam","method_name":"BAM"},{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1907.09701","atlas_url":"https://app.syntology.ai/?focus=1907.09701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.09701"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/google-research-datasets/bim","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research-datasets/bam","reach":null}],"summary":{"ran_honours":1,"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1},"listed":{"samples":1,"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":"2965857b8000dac0","entry":"get_global_indices","repo":"google-research-datasets/bam","repo_kind":"listed","path":"bam/metrics.py","file_url":"https://github.com/google-research-datasets/bam/blob/HEAD/bam/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2965857b8000dac0"}},{"code_sha256_prefix":"8db06832e6dbf0b6","entry":"corr_indices","repo":"google-research-datasets/bim","repo_kind":"official","path":"bam/metrics.py","file_url":"https://github.com/google-research-datasets/bim/blob/HEAD/bam/metrics.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":"8db06832e6dbf0b6"}},{"code_sha256_prefix":"a539b0fef0ed651a","entry":"load_imgs","repo":"google-research-datasets/bim","repo_kind":"official","path":"bam/attributions.py","file_url":"https://github.com/google-research-datasets/bim/blob/HEAD/bam/attributions.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":"a539b0fef0ed651a"}},{"code_sha256_prefix":"0ac8c7eece2eb98d","entry":"load_pos_neg_attr","repo":"google-research-datasets/bim","repo_kind":"official","path":"bam/metrics.py","file_url":"https://github.com/google-research-datasets/bim/blob/HEAD/bam/metrics.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":"0ac8c7eece2eb98d"}},{"code_sha256_prefix":"4afd748b2a52289d","entry":"single_attr","repo":"google-research-datasets/bim","repo_kind":"official","path":"bam/attributions.py","file_url":"https://github.com/google-research-datasets/bim/blob/HEAD/bam/attributions.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":"4afd748b2a52289d"}},{"code_sha256_prefix":"96c5223d1f404db5","entry":"visualize_pos_attr","repo":"google-research-datasets/bim","repo_kind":"official","path":"bam/attributions.py","file_url":"https://github.com/google-research-datasets/bim/blob/HEAD/bam/attributions.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":"96c5223d1f404db5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}