Argumentation based reinforcement learning for meta-knowledge extraction

Abstract Knowledge integration in distributed data mining has received widespread attention that aims to integrate inconsistent information locating on distributed sites. Traditional integration methods become ineffective since they are unable to generate global knowledge, support advanced integration strategy, or make prediction without individual classifiers. In this paper, we propose an argumentation based reinforcement learning method to handle this problem. Inspired by meta-learning, we integrate distributed knowledge and extract meta-knowledge that is agreed-upon knowledge consistent to all the agents. Specifically, two learning stages are introduced: argumentation based learning stage integrates and extracts meta-knowledge, and reinforcement learning stage evaluates and refines meta-knowledge. The two learning stages run alternately to extract global meta-knowledge base, which can be used to make prediction directly. The results from extensive experiments demonstrate that our method can extract refined meta-knowledge with a much satisfied performance.

[1]  Ivan Bratko,et al.  Argument based machine learning , 2006, Artif. Intell..

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

[3]  Fabrício Enembreck,et al.  Using Distributed Data Mining and Distributed Artificial Intelligence for Knowledge Integration , 2007, CIA.

[4]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[5]  Keith B. Hall,et al.  Correlated Q-Learning , 2003, ICML.

[6]  Mathieu Serrurier,et al.  Arguing and explaining classifications , 2007, AAMAS '07.

[7]  Trevor J. M. Bench-Capon,et al.  Arguing from experience using multiple groups of agents , 2011, Argument Comput..

[8]  Henri Prade,et al.  Using arguments for making and explaining decisions , 2009, Artif. Intell..

[9]  Jerzy Stefanowski,et al.  Addressing imbalanced data with argument based rule learning , 2015, Expert Syst. Appl..

[10]  Yoav Freund,et al.  Boosting a weak learning algorithm by majority , 1995, COLT '90.

[11]  Pat Langley,et al.  Estimating Continuous Distributions in Bayesian Classifiers , 1995, UAI.

[12]  Ricardo Vilalta,et al.  A Perspective View and Survey of Meta-Learning , 2002, Artificial Intelligence Review.

[13]  David Stuart Robertson,et al.  Argument-based applications to knowledge engineering , 2000, The Knowledge Engineering Review.

[14]  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..

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

[16]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[17]  Richard A. Berk.  Classification and Regression Trees (CART) , 2008 .

[18]  G. Ramaswamy,et al.  DISTRIBUTED DATA MINING AND AGENT MINING INTERACTION AND INTEGRATION: A NOVEL APPROACH , 2010 .

[19]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[20]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[21]  Analía Amandi,et al.  A reinforcement learning approach to improve the argument selection effectiveness in argumentation-based negotiation , 2013, Expert Syst. Appl..

[22]  Kallirroi Georgila,et al.  Reinforcement Learning of Argumentation Dialogue Policies in Negotiation , 2011, INTERSPEECH.

[23]  Frans Coenen,et al.  Data structure for association rule mining: T-trees and P-trees , 2004, IEEE Transactions on Knowledge and Data Engineering.

[24]  Ling Li,et al.  Distributed data mining: a survey , 2012, Inf. Technol. Manag..

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

[26]  Wynne Hsu,et al.  Integrating Classification and Association Rule Mining , 1998, KDD.

[27]  Haibo He,et al.  Incremental Learning From Stream Data , 2011, IEEE Transactions on Neural Networks.

[28]  Trevor J. M. Bench-Capon.  Value-based argumentation frameworks , 2002, NMR.

[29]  Li Yao,et al.  Argumentation Based Joint Learning: A Novel Ensemble Learning Approach , 2015, PloS one.

[30]  Ivan Bratko,et al.  Elicitation of neurological knowledge with argument-based machine learning , 2013, Artif. Intell. Medicine.

[31]  Carlos Angel Iglesias,et al.  A systematic review of argumentation techniques for multi-agent systems research , 2015, Artificial Intelligence Review.

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

[33]  Bart De Schutter,et al.  A Comprehensive Survey of Multiagent Reinforcement Learning , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[34]  Matthias Klusch,et al.  Distributed data mining and agents , 2005, Eng. Appl. Artif. Intell..

[35]  Trevor J. M. Bench-Capon,et al.  PISA: A framework for multiagent classification using argumentation , 2012, Data Knowl. Eng..

[36]  Trevor J. M. Bench-Capon,et al.  PADUA: a protocol for argumentation dialogue using association rules , 2009, Artificial Intelligence and Law.

[37]  Claudette Cayrol,et al.  On the Acceptability of Arguments in Preference-based Argumentation , 1998, UAI.

[38]  Robert P. W. Duin,et al.  Bagging for linear classifiers , 1998, Pattern Recognit..

[39]  Iryna Gurevych,et al.  Argumentation Mining in User-Generated Web Discourse , 2016, CL.

[40]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[41]  I. Nonaka,et al.  How Japanese Companies Create the Dynamics of Innovation , 1995 .