An Efficient Explanation of Individual Classifications using Game Theory
@article{trumbelj2010AnEE, title={An Efficient Explanation of Individual Classifications using Game Theory}, author={E. {\vS}trumbelj and I. Kononenko}, journal={J. Mach. Learn. Res.}, year={2010}, volume={11}, pages={1-18} }
We present a general method for explaining individual predictions of classification models. The method is based on fundamental concepts from coalitional game theory and predictions are explained with contributions of individual feature values. We overcome the method's initial exponential time complexity with a sampling-based approximation. In the experimental part of the paper we use the developed method on models generated by several well-known machine learning algorithms on both synthetic and… CONTINUE READING
Figures, Tables, and Topics from this paper
217 Citations
The Explanation Game: Explaining Machine Learning Models with Cooperative Game Theory
- Mathematics, Computer Science
- ArXiv
- 2019
- 11
- Highly Influenced
- PDF
The Explanation Game: Explaining Machine Learning Models Using Shapley Values
- Computer Science
- CD-MAKE
- 2020
- 10
Explaining prediction models and individual predictions with feature contributions
- Computer Science
- Knowledge and Information Systems
- 2013
- 237
A Game Theoretic Approach to Class-wise Selective Rationalization
- Computer Science, Mathematics
- NeurIPS
- 2019
- 11
- PDF
An exploration of the influence of path choice in game-theoretic attribution algorithms
- Computer Science, Mathematics
- ArXiv
- 2020
- PDF
Explainable Artificial Intelligence: How Subsets of the Training Data Affect a Prediction
- Computer Science, Mathematics
- ArXiv
- 2020
- Highly Influenced
- PDF
shapr: An R-package for explaining machine learning models with dependence-aware Shapley values
- Computer Science, Mathematics
- J. Open Source Softw.
- 2019
- 2
- PDF
Explaining individual predictions when features are dependent: More accurate approximations to Shapley values
- Mathematics, Computer Science
- ArXiv
- 2019
- 46
- PDF
References
SHOWING 1-10 OF 29 REFERENCES
Feature Selection via Coalitional Game Theory
- Mathematics, Computer Science
- Neural Computation
- 2007
- 75
- PDF
Explaining Classifications For Individual Instances
- Computer Science
- IEEE Transactions on Knowledge and Data Engineering
- 2008
- 180
- PDF
Polynomial calculation of the Shapley value based on sampling
- Mathematics, Computer Science
- Comput. Oper. Res.
- 2009
- 210
Explaining instance classifications with interactions of subsets of feature values
- Computer Science
- Data Knowl. Eng.
- 2009
- 61
- PDF
Fair Attribution of Functional Contribution in Artificial and Biological Networks
- Computer Science, Medicine
- Neural Computation
- 2004
- 100
- PDF
Contact personalization using a score understanding method
- Computer Science
- 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)
- 2008
- 33
- PDF