PISA: A framework for multiagent classification using argumentation

This paper describes an approach to multi-agent classification using an argumentation from experience paradigm whereby individual agents argue for a given example to be classified with a particular label according to their local data. Arguments are expressed in the form of classification rules which are generated dynamically. As such each local database can be conceptualised as an experience repository; and the individual classification rules, generated from this repository, as describing generalisations drawn from this experience. The argumentation process and the supporting data structures are fully described. The process has been implemented in the PISA (Pooling Information from Several Agents) multi-agent framework which is fully described. Experiments indicate that the operation of PISA is comparable with other classification approaches and that, when operating groups or in the presence of noise, PISA outperforms such comparable approaches.

[1]  Santiago Ontañón,et al.  Cooperative Multiagent Learning , 2002, Adaptive Agents and Multi-Agents Systems.

[2]  Pat Langley,et al.  Editorial: On Machine Learning , 1986, Machine Learning.

[3]  Eric Bauer,et al.  An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants , 1999, Machine Learning.

[4]  Trevor J. M. Bench-Capon,et al.  Arguments from Experience: The PADUA Protocol , 2008, COMMA.

[5]  Choh-Man Teng.  Evaluating Noise Correction , 2000, PRICAI.

[6]  John F. Horty,et al.  Reasons and precedent , 2011, ICAIL.

[7]  Frans Coenen,et al.  The effect of threshold values on association rule based classification accuracy , 2007, Data Knowl. Eng..

[8]  J. Ross Quinlan,et al.  Combining Instance-Based and Model-Based Learning , 1993, ICML.

[9]  Kin Keung Lai,et al.  Credit risk assessment with a multistage neural network ensemble learning approach , 2008, Expert Syst. Appl..

[10]  Javed Mostafa,et al.  A comparison between single-agent and multi-agent classification of documents , 2001, Proceedings 15th International Parallel and Distributed Processing Symposium. IPDPS 2001.

[11]  Nicolás Marín,et al.  TBAR: An efficient method for association rule mining in relational databases , 2001, Data Knowl. Eng..

[12]  Trevor J. M. Bench-Capon,et al.  A model of legal reasoning with cases incorporating theories and values , 2003, Artif. Intell..

[13]  Trevor J. M. Bench-Capon,et al.  Multi-Party Argument from Experience , 2009, ArgMAS.

[14]  Carlos Iván Chesñevar,et al.  Integrating Defeasible Argumentation and Machine Learning Techniques , 2004, ArXiv.

[15]  L. Wittgenstein.  The Blue and Brown Books , 1958 .

[16]  Santiago Ontañón,et al.  Learning, Information Exchange, and Joint-Deliberation through Argumentation in Multi-agent Systems , 2008, OTM Workshops.

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

[18]  Wei-Min Shen,et al.  Collaborative multiagent learning for classification tasks , 2001, AGENTS '01.

[19]  Thomas G. Dietterich.  An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization , 2000, Machine Learning.

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

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

[22]  Andrea Omicini,et al.  Co-argumentation Artifact for Agent Societies , 2007, ArgMAS.

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

[24]  Rakesh Agrawal,et al.  Privacy-preserving data mining , 2000, SIGMOD 2000.

[25]  Henry Prakken,et al.  DOI: 10.1017/S000000000000000 Printed in the United Kingdom Formal systems for persuasion dialogue , 2022 .

[26]  Frans Coenen,et al.  Obtaining best parameter values for accurate classification , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[27]  Kevin D. Ashley,et al.  A case-based approach to modeling legal expertise , 1988, IEEE Expert.

[28]  Rom Harré,et al.  The Principles of Linguistic Philosophy , 1965 .

[29]  Lukasz A. Kurgan,et al.  A tree-projection-based algorithm for multi-label recurrent-item associative-classification rule generation , 2008, Data Knowl. Eng..

[30]  Daniel A. Keim,et al.  On Knowledge Discovery and Data Mining , 1997 .

[31]  D. Opitz,et al.  Popular Ensemble Methods: An Empirical Study , 1999, J. Artif. Intell. Res..

[32]  Nancy L. Green,et al.  Causal argumentation schemes to support sense-making in clinical genetics and law , 2011, ICAIL.

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

[34]  Pietro Baroni,et al.  AFRA: Argumentation framework with recursive attacks , 2011, Int. J. Approx. Reason..

[35]  Thomas G. Dietterich,et al.  Error-Correcting Output Coding Corrects Bias and Variance , 1995, ICML.

[36]  G DietterichThomas.  An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees , 2000 .

[37]  Peter Clark,et al.  The CN2 Induction Algorithm , 1989, Machine Learning.

[38]  Gemma Bel-Enguix,et al.  Membranes as multi-agent systems: an application to dialogue modelling , 2006 .

[39]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

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

[41]  Henry Prakken,et al.  An abstract framework for argumentation with structured arguments , 2010, Argument Comput..

[42]  Andrea Omicini,et al.  Argumentation and Artifact for Dialogue Support , 2009, ArgMAS.

[43]  Vladimir Gorodetsky,et al.  Multi-agent technology for distributed data mining and classification , 2003, IEEE/WIC International Conference on Intelligent Agent Technology, 2003. IAT 2003..

[44]  Philip K. Chan,et al.  Meta-learning in distributed data mining systems: Issues and approaches , 2007 .

[45]  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..

[46]  Carla E. Brodley,et al.  Identifying and Eliminating Mislabeled Training Instances , 1996, AAAI/IAAI, Vol. 1.

[47]  Frans Coenen,et al.  EMADS: An extendible multi-agent data miner , 2009, Knowl. Based Syst..

[48]  Ramakrishnan Srikant,et al.  Fast Algorithms for Mining Association Rules in Large Databases , 1994, VLDB.

[49]  Ann Macintosh,et al.  Argument Visualization for eParticipation: Towards a Research Agenda and Prototype Tool , 2011, ePart.

[50]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[51]  Thomas F. Gordon,et al.  The pleadings game: formalizing procedural justice , 1993, ICAIL '93.

[52]  Santiago Ontañón,et al.  An Argumentation-Based Framework for Deliberation in Multi-agent Systems , 2007, ArgMAS.

[53]  Ignacio Olmeda,et al.  Hybrid Classifiers for Financial Multicriteria Decision Making: The Case of Bankruptcy Prediction , 1997 .

[54]  Geoffrey I. Webb,et al.  MultiBoosting: A Technique for Combining Boosting and Wagging , 2000, Machine Learning.

[55]  Choh-Man Teng,et al.  Correcting Noisy Data , 1999, ICML.

[56]  Vipin Kumar,et al.  A simple statistical model and association rule filtering for classification , 2011, KDD.

[57]  Vincent A. W. M. M. Aleven,et al.  Teaching case-based argumentation through a model and examples , 1997 .

[58]  Thomas G. Dietterich.  Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[59]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

[60]  Raymond J. Mooney,et al.  Constructing Diverse Classifier Ensembles using Artificial Training Examples , 2003, IJCAI.

[61]  Jian Pei,et al.  Mining frequent patterns without candidate generation , 2000, SIGMOD 2000.

[62]  Trevor J. M. Bench-Capon,et al.  Argumentation in artificial intelligence , 2007, Artif. Intell..