{"doi":"10.1609/aaai.v35i13.17358","title":"Explaining A Black-box By Using A Deep Variational Information Bottleneck Approach","abstract":"Interpretable machine learning has gained much attention recently. Briefness and comprehensiveness are necessary in order to provide a large amount of information concisely when explaining a black-box decision system. However, existing interpretable machine learning methods fail to consider briefness and comprehensiveness simultaneously, leading to redundant explanations. We propose the variational information bottleneck for interpretation, VIBI, a system-agnostic interpretable method that provides a brief but comprehensive explanation. VIBI adopts an information theoretic principle, information bottleneck principle, as a criterion for finding such explanations. For each instance, VIBI selects key features that are maximally compressed about an input (briefness), and informative about a decision made by a black-box system on that input (comprehensive). We evaluate VIBI on three datasets and compare with state-of-the-art interpretable machine learning methods in terms of both interpretability and fidelity evaluated by human and quantitative metrics.","journal":"Proceedings of the AAAI Conference on Artificial Intelligence","year":2021,"id":212902,"datarank":0.6307038929086449,"base_score":4.204692619390966,"endowment":4.204692619390966,"self_citation_contribution":0.6307038929086449,"citation_network_contribution":0.0,"self_endowment_contribution":0.6307038929086449,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":66,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9458,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2021-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":804080,"name":"Pengtao Xie","orcid":"0000-0003-0521-174X","position":1,"is_corresponding":false},{"id":374935,"name":"Heewook Lee","orcid":"0000-0002-3528-6833","position":2,"is_corresponding":false},{"id":762216,"name":"Wei Wu","orcid":"0000-0003-1424-1414","position":3,"is_corresponding":false},{"id":18781,"name":"Eric P. Xing","orcid":"0009-0005-9158-4201","position":4,"is_corresponding":false},{"id":804079,"name":"Seojin Bang","orcid":"0000-0003-2521-5051","position":0,"is_corresponding":true}],"reference_count":55,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-18T23:52:31.378994Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}