Abduction and Argumentation for Explainable Machine Learning: A Position Survey

This paper presents Abduction and Argumentation as two principled forms for reasoning, and fleshes out the fundamental role that they can play within Machine Learning. It reviews the state-of-the-art work over the past few decades on the link of these two reasoning forms with machine learning work, and from this it elaborates on how the explanation-generating role of Abduction and Argumentation makes them naturally-fitting mechanisms for the development of Explainable Machine Learning and AI systems. Abduction contributes towards this goal by facilitating learning through the transformation, preparation, and homogenization of data. Argumentation, as a conservative extension of classical deductive reasoning, offers a flexible prediction and coverage mechanism for learning -- an associated target language for learned knowledge -- that explicitly acknowledges the need to deal, in the context of learning, with uncertain, incomplete and inconsistent data that are incompatible with any classically-represented logical theory.

[1]  Stephen Muggleton,et al.  Theory Completion Using Inverse Entailment , 2000, ILP.

[2]  G. Harman,et al.  The Problem of Induction , 2006 .

[3]  Stephen Muggleton,et al.  Chapter Four – Construction and Validation of Food Webs Using Logic-Based Machine Learning and Text Mining , 2013 .

[4]  Francesca Toni,et al.  Abstract Argumentation for Case-Based Reasoning , 2016, KR.

[5]  Loizos Michael.  The Advice Taker 2.0 , 2017, COMMONSENSE.

[6]  Oliver Ray,et al.  Inferring the Function of Genes from Synthetic Lethal Mutations , 2008, 2008 International Conference on Complex, Intelligent and Software Intensive Systems.

[7]  Joao Marques-Silva,et al.  A SAT-Based Approach to Learn Explainable Decision Sets , 2018, IJCAR.

[8]  Lucas Carstens,et al.  Using Argumentation to Improve Classification in Natural Language Problems , 2017, ACM Trans. Internet Techn..

[9]  Jure Leskovec,et al.  Interpretable Decision Sets: A Joint Framework for Description and Prediction , 2016, KDD.

[10]  Loizos Michael,et al.  Causal Learnability , 2011, IJCAI.

[11]  Francisco Herrera,et al.  Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI , 2020, Inf. Fusion.

[12]  Krysia Broda,et al.  An Abductive-Inductive Algorithm for Probabilistic Inductive Logic Programming , 2016, ILP.

[13]  Evelina Lamma,et al.  Integrating Induction and Abduction in Logic Programming , 1999, Inf. Sci..

[14]  Yang Gao,et al.  Argumentation accelerated reinforcement learning , 2014 .

[15]  J. Dessalles,et al.  Arguing, reasoning, and the interpersonal (cultural) functions of human consciousness , 2011, Behavioral and Brain Sciences.

[16]  E. Mark Gold,et al.  Language Identification in the Limit , 1967, Inf. Control..

[17]  Paolo Mancarella,et al.  Abductive Logic Programming , 1992, LPNMR.

[18]  Yang Gao,et al.  Argumentation Accelerated Reinforcement Learning for RoboCup Keepaway-Takeaway , 2013, TAFA.

[19]  Marc Denecker,et al.  AILP: Abductive Inductive Logic Programming , 1995, IJCAI.

[20]  Leslie G. Valiant,et al.  A First Experimental Demonstration of Massive Knowledge Infusion , 2008, KR.

[21]  Sanjay Modgil,et al.  Reasoning about preferences in argumentation frameworks , 2009, Artif. Intell..

[22]  Katsumi Inoue,et al.  Induction as Consequence Finding , 2004, Machine Learning.

[23]  Akihiro Yamamoto,et al.  Finding Hypotheses from Examples by Computing the Least Generalization of Bottom Clauses , 1998, Discovery Science.

[24]  Ivan Bratko,et al.  Argument Based Machine Learning in a Medical Domain , 2006, COMMA.

[25]  Loizos Michael,et al.  Neural-Symbolic Integration: A Compositional Perspective , 2020, AAAI.

[26]  Zhi-Hua Zhou,et al.  Bridging Machine Learning and Logical Reasoning by Abductive Learning , 2019, NeurIPS.

[27]  Santiago Ontañón,et al.  Coordinated inductive learning using argumentation-based communication , 2015, Autonomous Agents and Multi-Agent Systems.

[28]  Dalal Alrajeh,et al.  Using abduction and induction for operational requirements elaboration , 2009, J. Appl. Log..

[29]  Stephen Anthony Moyle.  An investigation into theory completion techniques in inductive logic programming , 2003 .

[30]  David Hume.  A Treatise of Human Nature: Being an Attempt to introduce the experimental Method of Reasoning into Moral Subjects , 1972 .

[31]  Francesca Toni,et al.  Argumentation for Machine Learning: A Survey , 2016, COMMA.

[32]  Krysia Broda,et al.  Hybrid Abductive Inductive Learning: A Generalisation of Progol , 2003, ILP.

[33]  Loizos Michael,et al.  Cognitive Reasoning and Learning Mechanisms , 2016, AIC.

[34]  Francesca Toni,et al.  Improving Out-of-Domain Sentiment Polarity Classification Using Argumentation , 2015, 2015 IEEE International Conference on Data Mining Workshop (ICDMW).

[35]  Ronald L. Rivest,et al.  Learning decision lists , 2004, Machine Learning.

[36]  Taisuke Sato,et al.  Statistical Abduction with Tabulation , 2002, Computational Logic: Logic Programming and Beyond.

[37]  Antonis C. Kakas,et al.  Learning Non-Monotonic Logic Programs: Learning Exceptions , 1995, ECML.

[38]  Oliver Ray,et al.  Nonmonotonic abductive inductive learning , 2009, J. Appl. Log..

[39]  Mathieu Serrurier,et al.  Agents that argue and explain classifications , 2007, Autonomous Agents and Multi-Agent Systems.

[40]  Trevor J. M. Bench-Capon,et al.  Argument Based Machine Learning Applied to Law , 2005, Artificial Intelligence and Law.

[41]  Phan Minh Dung,et al.  On the Acceptability of Arguments and its Fundamental Role in Nonmonotonic Reasoning, Logic Programming and n-Person Games , 1995, Artif. Intell..

[42]  Luc De Raedt,et al.  Multiple Predicate Learning in Two Inductive Logic Programming Settings , 1996, Log. J. IGPL.

[43]  Alessandra Russo,et al.  Inductive Logic Programming as Abductive Search , 2010, ICLP.

[44]  Ivan Bratko,et al.  Argument-Based Machine Learning , 2006, ISMIS.

[45]  Chiaki Sakama.  Abduction in argumentation frameworks , 2018, J. Appl. Non Class. Logics.

[46]  Matti Järvisalo,et al.  Synthesizing Argumentation Frameworks from Examples , 2019, ECAI.

[47]  Antonis C. Kakas,et al.  Argumentation based decision making for autonomous agents , 2003, AAMAS '03.

[48]  Santiago Ontañón,et al.  A defeasible reasoning model of inductive concept learning from examples and communication , 2012, Artif. Intell..

[49]  Leslie G. Valiant,et al.  Autodidactic learning and reasoning , 2008 .

[50]  Akihiro Yamamoto,et al.  Which Hypotheses Can Be Found with Inverse Entailment? , 1997, ILP.

[51]  Oliver Ray,et al.  Abductive Logic Programming in the Clinical Management of HIV/AIDS , 2006, ECAI.

[52]  Fabrizio Riguzzi,et al.  Abductive concept learning , 2000, New Generation Computing.

[53]  Joao Marques-Silva,et al.  Abduction-Based Explanations for Machine Learning Models , 2018, AAAI.

[54]  Carlos Iván Chesñevar,et al.  A Hybrid Approach To Pattern Classification Using Neural Networks and Defeasible Argumentation , 2004, FLAIRS.

[55]  Paolo Mancarella,et al.  On Argumentation Logic and Propositional Logic , 2018, Stud Logica.

[56]  Loizos Michael,et al.  Simultaneous Learning and Prediction , 2014, KR.

[57]  Nicoletta Prentzas,et al.  Integrating Machine Learning with Symbolic Reasoning to Build an Explainable AI Model for Stroke Prediction , 2019, 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE).

[58]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.

[59]  Franco Turini,et al.  A Survey of Methods for Explaining Black Box Models , 2018, ACM Comput. Surv..

[60]  Peter A. Flach,et al.  Abductive and inductive reasoning: background and issues , 2000 .

[61]  Ivan Bratko,et al.  Argument Based Machine Learning from Examples and Text , 2009, 2009 First Asian Conference on Intelligent Information and Database Systems.

[62]  Yang Gao,et al.  Argumentation Accelerated Reinforcement Learning for Cooperative Multi-Agent Systems , 2014, ECAI.