Article

Extracting decision trees from trained neural networks

Author:

Olcay BozAuthors Info & Claims

KDD '02: Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining

Pages 456 - 461

https://doi.org/10.1145/775047.775113

Published: 23 July 2002 Publication History

Get Access

Abstract

Neural Networks are successful in acquiring hidden knowledge in datasets. Their biggest weakness is that the knowledge they acquire is represented in a form not understandable to humans. Researchers tried to address this problem by extracting rules from trained Neural Networks. Most of the proposed rule extraction methods required specialized type of Neural Networks; some required binary inputs and some were computationally expensive. Craven proposed extracting MofN type Decision Trees from Neural Networks. We believe MofN type Decision Trees are only good for MofN type problems and trees created for regular high dimensional real world problems may be very complex. In this paper, we introduced a new method for extracting regular C4.5 like Decision Trees from trained Neural Networks. We showed that the new method (DecText) is effective in extracting high fidelity trees from trained networks. We also introduced a new discretization technique to make DecText be able to handle continuous features and a new pruning technique for finding simplest tree with the highest fidelity.

References

[1]

L. Atlas, R. Cole, J. Connor, M. El-Sharkawi, R. J. Marks, V. Muthusamy, and E. Barnard. Performance comparisons between backpropagation networks and classification trees on three real-world applications. In Advances in Neural Information Processing Systems, volume 2, pages 622--629, 1990.

Digital Library

Google Scholar

[2]

O. Boz. Converting A Trained Neural Network To A Decision Tree DecText - Decision Tree Etxractor. PhD thesis, Computer Science and Engineering, Lehigh University, 2000.

Digital Library

Google Scholar

[3]

W. Buntine and T. Niblett. A further comparison of splitting rules for decision-tree induction. Machine Learning, 8:75, 1992.

Digital Library

Google Scholar

[4]

M. W. Craven. Extracting Comprehensible Models from Trained Neural Networks. PhD thesis, Department of Computer Sciences, University of Wisconsin-Madison, 1996. (Also appears as UW Technical Report CS-TR-96-1326).

Digital Library

Google Scholar

[5]

M. W. Craven and J. W. Shavlik. Extracting tree-structured representations of trained networks. In Advances in Neural Information Processing Systems, volume 8, pages 24--30, Denver, CO, 1996. MIT Press.

Google Scholar

[6]

D. Fisher and K. McKusick. An emprical comparison of id3 and back propagation. In Proceedings of the eleventh international Joint Conference on Artificial Intelligence, pages 788--793, Detroit, 1989. Morgan Kaufmann.

Google Scholar

[7]

P. Murphy and M. Pazzani. Id2-of-3: Constructive induction of n-of-m concepts for discriminators in decision trees. In Proceedings of the Eighth International Machine learning Workshop, pages 183--187, Evanston, IL, 1991. Morgan Kaufmann.

Crossref

Google Scholar

[8]

J. W. Shavlik, R. J. Mooney, and G. G. Towell. Symbolic and neural learning algorithms: An experimental comparison. Machine Learning, 6:111--143, 1991.

Digital Library

Google Scholar

[9]

B. W. Silverman. Density Estimation for Statistics and Data Analysis. Chapman & Hall, London, 1986.

Crossref

Google Scholar

[10]

S. M. Weiss and I. Kapouleas. An empirical comparison of pattern recognition, neural nets, and machine learning classification methods. In J. W. Shavlik and T. G. Dietterich, editors, Readings in Machine Learning. Morgan Kaufman, San Mateo, CA, 1990.

Google Scholar

Cited By

View all

Nougnanke BLabit YBruyere MAivodji UFerlin S(2023)ML-Based Performance Modeling in SDN-Enabled Data Center NetworksIEEE Transactions on Network and Service Management10.1109/TNSM.2022.319778920:1(815-829)Online publication date: Mar-2023
https://doi.org/10.1109/TNSM.2022.3197789
Zhang DXu YPeng YDu CWang NTang MLu LLiu J(2023)An Interpretable Station Delay Prediction Model Based on Graph Community Neural Network and Time-Series Fuzzy Decision TreeIEEE Transactions on Fuzzy Systems10.1109/TFUZZ.2022.318145331:2(421-433)Online publication date: Feb-2023
https://doi.org/10.1109/TFUZZ.2022.3181453
Sewunetie WKovács L(2023)Efficiency Evaluation of ChatGPT for Adverb Type Categorization2023 World Symposium on Digital Intelligence for Systems and Machines (DISA)10.1109/DISA59116.2023.10308928(199-203)Online publication date: 21-Sep-2023
https://doi.org/10.1109/DISA59116.2023.10308928
Show More Cited By

Recommendations

Extracting symbolic rules from trained neural network ensembles
Artificial Intelligence Advances in China

Neural network ensemble can significantly improve the generalization ability of neural network based systems. However, its comprehensibility is even worse than that of a single neural network because it comprises a collection of individual neural ...
Extracting symbolic rules from trained neural network ensembles
Special issue on Artificial intelligence advances in China

Neural network ensemble can significantly improve the generalization ability of neural network based systems. However, its comprehensibility is even worse than that of a single neural network because it comprises a collection of individual neural ...
Extracting rules from trained neural networks

Presents an algorithm for extracting rules from trained neural networks. The algorithm is a decompositional approach which can be applied to any neural network whose output function is monotone such as a sigmoid function. Therefore, the algorithm can be ...

Comments

Information & Contributors

Information

Published In

KDD '02: Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining

July 2002

719 pages

ISBN:158113567X

DOI:10.1145/775047

Conference Chair:
Osmar R. Zaïane
University of Alberta, Canada
,
General Chair:
Randy Goebel
University of Alberta, Canada
,
Program Chairs:
David Hand
Imperial College, UK
,
Daniel Keim
AT&T
,
Raymond Ng
University of British Columbia, Canada

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 23 July 2002

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Article

Conference

KDD02

Sponsor:

KDD02: The Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

July 23 - 26, 2002

Alberta, Edmonton, Canada

Acceptance Rates

KDD '02 Paper Acceptance Rate 44 of 307 submissions, 14%;

Overall Acceptance Rate 1,133 of 8,635 submissions, 13%

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

63
Total Citations
View Citations
1,836
Total Downloads

Downloads (Last 12 months)62
Downloads (Last 6 weeks)3

Reflects downloads up to 23 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Nougnanke BLabit YBruyere MAivodji UFerlin S(2023)ML-Based Performance Modeling in SDN-Enabled Data Center NetworksIEEE Transactions on Network and Service Management10.1109/TNSM.2022.319778920:1(815-829)Online publication date: Mar-2023
https://doi.org/10.1109/TNSM.2022.3197789
Zhang DXu YPeng YDu CWang NTang MLu LLiu J(2023)An Interpretable Station Delay Prediction Model Based on Graph Community Neural Network and Time-Series Fuzzy Decision TreeIEEE Transactions on Fuzzy Systems10.1109/TFUZZ.2022.318145331:2(421-433)Online publication date: Feb-2023
https://doi.org/10.1109/TFUZZ.2022.3181453
Sewunetie WKovács L(2023)Efficiency Evaluation of ChatGPT for Adverb Type Categorization2023 World Symposium on Digital Intelligence for Systems and Machines (DISA)10.1109/DISA59116.2023.10308928(199-203)Online publication date: 21-Sep-2023
https://doi.org/10.1109/DISA59116.2023.10308928
Zhang BDong ZZhang JLin H(2023)Functional network: A novel framework for interpretability of deep neural networksNeurocomputing10.1016/j.neucom.2022.11.035519(94-103)Online publication date: Jan-2023
https://doi.org/10.1016/j.neucom.2022.11.035
Nápoles GHoitsma FKnoben AJastrzebska ALeon Espinosa M(2023)Prolog-based agnostic explanation module for structured pattern classificationInformation Sciences10.1016/j.ins.2022.12.012622(1196-1227)Online publication date: Apr-2023
https://doi.org/10.1016/j.ins.2022.12.012
Bodria FGiannotti FGuidotti RNaretto FPedreschi DRinzivillo S(2023)Benchmarking and survey of explanation methods for black box modelsData Mining and Knowledge Discovery10.1007/s10618-023-00933-937:5(1719-1778)Online publication date: 3-Jun-2023
https://doi.org/10.1007/s10618-023-00933-9
Reeder SJensen JBall R(2023)Evaluating Explainable AI (XAI) in Terms of User Gender and Educational BackgroundArtificial Intelligence in HCI10.1007/978-3-031-35891-3_18(286-304)Online publication date: 9-Jul-2023
https://doi.org/10.1007/978-3-031-35891-3_18
Giannotti FNaretto FBodria F(2023)Explainable for Trustworthy AIHuman-Centered Artificial Intelligence10.1007/978-3-031-24349-3_10(175-195)Online publication date: 4-Apr-2023
https://doi.org/10.1007/978-3-031-24349-3_10
Vouros G(2022)Explainable Deep Reinforcement Learning: State of the Art and ChallengesACM Computing Surveys10.1145/352744855:5(1-39)Online publication date: 3-Dec-2022
https://dl.acm.org/doi/10.1145/3527448
Orphanou KOtterbacher JKleanthous SBatsuren KGiunchiglia FBogina VTal AHartman AKuflik T(2022)Mitigating Bias in Algorithmic Systems—A Fish-eye ViewACM Computing Surveys10.1145/352715255:5(1-37)Online publication date: 3-Dec-2022
https://dl.acm.org/doi/10.1145/3527152
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Extracting symbolic rules from trained neural network ensembles

Extracting symbolic rules from trained neural network ensembles

Extracting rules from trained neural networks