{"id":752719,"date":"2021-06-04T16:05:06","date_gmt":"2021-06-04T23:05:06","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&p=752719"},"modified":"2021-06-30T23:21:16","modified_gmt":"2021-07-01T06:21:16","slug":"extune-explaining-tuple-non-conformance-sigmod-2020-talk","status":"publish","type":"msr-video","link":"https:\/\/www.microsoft.com\/en-us\/research\/video\/extune-explaining-tuple-non-conformance-sigmod-2020-talk\/","title":{"rendered":"ExTuNe: Explaining Tuple Non-conformance"},"content":{"rendered":"

Authors: Anna Fariha, Ashish Tiwari, Arjun Radhakrishna, Sumit Gulwani<\/p>\n

Abstract: In data-driven systems, we often encounter tuples on which the predictions of a machine-learned model are untrustworthy. A key cause of such untrustworthiness is non-conformance of a new tuple with respect to the training dataset. To check conformance, we introduce a novel concept of data invariant, which captures a set of implicit constraints that all tuples of a dataset satisfy: a test tuple is non-conforming if it violates the data invariants. Data invariants model complex relationships among multiple attributes; but do not provide interpretable explanations of non-conformance. We present ExTuNe, a system for Explaining causes of Tuple Non-conformance. Based on the principles of causality, ExTuNe assigns responsibility to the attributes for causing non-conformance. The key idea is to observe change in invariant violation under intervention on attribute-values. Through a simple interface, ExTuNe produces a ranked list of the test tuples based on their degree of non-conformance and visualizes tuple-level attribute responsibility for non-conformance through heat maps. ExTuNe further visualizes attribute responsibility, aggregated over the test tuples. We demonstrate how ExTuNe can detect and explain tuple non-conformance and assist the users to make careful decisions towards achieving trusted machine learning.<\/p>\n

Paper link: https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3318464.3384694<\/p>\n","protected":false},"excerpt":{"rendered":"

Authors: Anna Fariha, Ashish Tiwari, Arjun Radhakrishna, Sumit Gulwani Abstract: In data-driven systems, we often encounter tuples on which the predictions of a machine-learned model are untrustworthy. A key cause of such untrustworthiness is non-conformance of a new tuple with respect to the training dataset. To check conformance, we introduce a novel concept of data […]<\/p>\n","protected":false},"featured_media":752722,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13563],"msr-video-type":[],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-752719","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-research-area-data-platform-analytics","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/www.youtube.com\/watch?v=wYzGDgQ1itE","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/752719"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-video"}],"version-history":[{"count":3,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/752719\/revisions"}],"predecessor-version":[{"id":752758,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/752719\/revisions\/752758"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/752722"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=752719"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=752719"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=752719"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=752719"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=752719"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=752719"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}