|   | 
Details
   web
Records
Author (up) Bertossi, L.
Title Declarative Approaches to Counterfactual Explanations for Classification Type
Year 2022 Publication Theory and Practice of Logic Programming Abbreviated Journal Theory Pract. Log. Program.
Volume Early Access Issue Pages
Keywords classification; explanations; counterfactuals; causality; answer-set programming; constraints
Abstract We propose answer-set programs that specify and compute counterfactual interventions on entities that are input on a classification model. In relation to the outcome of the model, the resulting counterfactual entities serve as a basis for the definition and computation of causality-based explanation scores for the feature values in the entity under classification, namely responsibility scores. The approach and the programs can be applied with black-box models, and also with models that can be specified as logic programs, such as rule-based classifiers. The main focus of this study is on the specification and computation of best counterfactual entities, that is, those that lead to maximum responsibility scores. From them one can read off the explanations as maximum responsibility feature values in the original entity. We also extend the programs to bring into the picture semantic or domain knowledge. We show how the approach could be extended by means of probabilistic methods, and how the underlying probability distributions could be modified through the use of constraints. Several examples of programs written in the syntax of the DLV ASP-solver, and run with it, are shown.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1471-0684 ISBN Medium
Area Expedition Conference
Notes WOS:000734688600001 Approved
Call Number UAI @ alexi.delcanto @ Serial 1515
Permanent link to this record
 

 
Author (up) Bertossi, L.
Title Specifying and computing causes for query answers in databases via database repairs and repair-programs Type
Year 2021 Publication Knowledge And Information Systems Abbreviated Journal Knowl. Inf. Syst.
Volume 63 Issue Pages 199231
Keywords Causality; Databases; Repairs; Constraints; Answer-set programming
Abstract There is a recently established correspondence between database tuples as causes for query answers in databases and tuple-based repairs of inconsistent databases with respect to denial constraints. In this work, answer-set programs that specify database repairs are used as a basis for solving computational and reasoning problems around causality in databases, including causal responsibility. Furthermore, causes are introduced also at the attribute level by appealing to an attribute-based repair semantics that uses null values. Corresponding repair-programs are introduced, and used as a basis for computation and reasoning about attribute-level causes. The answer-set programs are extended in order to capture causality under integrity constraints.
Address [Bertossi, Leopoldo] Adolfo Ibanez Univ, Fac Engn & Sci, Santiago, Chile, Email: leopoldo.bertossi@uai.cl
Corporate Author Thesis
Publisher Springer London Ltd Place of Publication Editor
Language English Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0219-1377 ISBN Medium
Area Expedition Conference
Notes WOS:000584967200001 Approved
Call Number UAI @ alexi.delcanto @ Serial 1258
Permanent link to this record
 

 
Author (up) Bertossi, L.; Geerts, F.
Title Data Quality and Explainable AI Type
Year 2020 Publication Acm Journal Of Data And Information Quality Abbreviated Journal ACM J. Data Inf. Qual.
Volume 12 Issue 2 Pages 11
Keywords Machine learning; causes; fairness; bias
Abstract In this work, we provide some insights and develop some ideas, with few technical details, about the role of explanations in Data Quality in the context of data-based machine learning models (ML). In this direction, there are, as expected, roles for causality, and explainable artificial intelligence. The latter area not only sheds light on the models, but also on the data that support model construction. There is also room for defining, identifying, and explaining errors in data, in particular, in ML, and also for suggesting repair actions. More generally, explanations can be used as a basis for defining dirty data in the context of ML, and measuring or quantifying them. We think dirtiness as relative to the ML task at hand, e.g., classification.
Address [Bertossi, Leopoldo] Univ Adolfo Ibanez, Fac Engn & Sci, Santiago, Chile, Email: leopoldo.bertossi@uai.cl;
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1936-1955 ISBN Medium
Area Expedition Conference
Notes WOS:000582595600005 Approved
Call Number UAI @ eduardo.moreno @ Serial 1308
Permanent link to this record
 

 
Author (up) Bertossi, L.; Li, J.; Schleich, M.; Suciu, D.; Vagena, Z.
Title Causality-based Explanation of Classification Outcomes Type
Year 2020 Publication DEEM'20: Proceedings of the Fourth International Workshop on Data Management for End-to-End Machine Learning Abbreviated Journal DEEM 2020
Volume 6 Issue Pages 1-10
Keywords
Abstract
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 9781450380232 Medium
Area Expedition Conference
Notes Approved
Call Number UAI @ eduardo.moreno @ Serial 1309
Permanent link to this record
 

 
Author (up) Livshits, E.; Bertossi, L.; Kimefeld, B.; Sebag, M.
Title The Shapley Value of Tuples in Query Answering Type
Year 2021 Publication Logical Methods in Computer Science Abbreviated Journal Log. Methods Comput. Sci.
Volume 17 Issue 3 Pages 22
Keywords Shapley value; query answering; conjunctive queries; aggregate queries
Abstract We investigate the application of the Shapley value to quantifying the contribution of a tuple to a query answer. The Shapley value is a widely known numerical measure in cooperative game theory and in many applications of game theory for assessing the contribution of a player to a coalition game. It has been established already in the 1950s, and is theoretically justified by being the very single wealth-distribution measure that satisfies some natural axioms. While this value has been investigated in several areas, it received little attention in data management. We study this measure in the context of conjunctive and aggregate queries by defining corresponding coalition games. We provide algorithmic and complexity-theoretic results on the computation of Shapley-based contributions to query answers; and for the hard cases we present approximation algorithms.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1868-8969 ISBN Medium
Area Expedition Conference
Notes WOS:000701675700007 Approved
Call Number UAI @ eduardo.moreno @ Serial 1310
Permanent link to this record
 

 
Author (up) Livshits, E.; Bertossi, L.; Kimelfeld, B.; Sebag, M.
Title Query Games in Databases Type
Year 2021 Publication Sigmod Record Abbreviated Journal Sigmod Rec.
Volume 50 Issue 1 Pages 78-85
Keywords RESPONSIBILITY; ANSWERS; BLAME
Abstract Database tuples can be seen as players in the game of jointly realizing the answer to a query. Some tuples may contribute more than others to the outcome, which can be a binary value in the case of a Boolean query, a number for a numerical aggregate query, and so on. To quantify the contributions of tuples, we use the Shapley value that was introduced in cooperative game theory and has found applications in a plethora of domains. Specifically, the Shapley value of an individual tuple quantifies its contribution to the query. We investigate the applicability of the Shapley value in this setting, as well as the computational aspects of its calculation in terms of complexity, algorithms, and approximation.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0163-5808 ISBN Medium
Area Expedition Conference
Notes WOS:000737738900017 Approved
Call Number UAI @ alexi.delcanto @ Serial 1517
Permanent link to this record