Logic Constraints to Feature Importances

In recent years, Artificial Intelligence (AI) algorithms have been proven to outperform traditional statistical methods in terms of predictivity, especially when a large amount of data was available. Nevertheless, the ”black box” nature of AI models is often a limit for a reliable application in high-stakes fields like diagnostic techniques, autonomous guide, etc. Recent works have shown that an adequate level of interpretability could enforce the more general concept of model trustworthiness [1]. The basic idea of this paper is to exploit the human prior knowledge of the features’ importance for a specific task, in order to coherently aid the phase of the model’s fitting. This sort of ”weighted” AI is obtained by extending the empirical loss with a regularization term encouraging the importance of the features to follow predetermined constraints. This procedure relies on local methods for the feature importance computation, e.g. LRP, LIME, etc. that are the link between the model weights to be optimized and the user-defined constraints on feature importance. In the fairness area, promising experimental results have been obtained for the Adult dataset. Many other possible applications of this model agnostic theoretical framework are described.

[1]  Ankur Taly,et al.  Gradients of Counterfactuals , 2016, ArXiv.

[2]  En-Jui Lee,et al.  Classification of Seismic Windows Using Artificial Neural Networks , 2011, ICCS.

[3]  Toon Calders,et al.  Why Unbiased Computational Processes Can Lead to Discriminative Decision Procedures , 2013, Discrimination and Privacy in the Information Society.

[4]  Wojciech Samek,et al.  Methods for interpreting and understanding deep neural networks , 2017, Digit. Signal Process..

[5]  Krishna P. Gummadi,et al.  The Case for Process Fairness in Learning: Feature Selection for Fair Decision Making , 2016 .

[6]  Alexander Binder,et al.  On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation , 2015, PloS one.

[7]  Erik Strumbelj,et al.  Explaining prediction models and individual predictions with feature contributions , 2014, Knowledge and Information Systems.

[8]  Erik Strumbelj,et al.  An Efficient Explanation of Individual Classifications using Game Theory , 2010, J. Mach. Learn. Res..

[9]  Avanti Shrikumar,et al.  Learning Important Features Through Propagating Activation Differences , 2017, ICML.

[10]  Xiaobing Peng,et al.  A Novel Feature Weighted Strategy on Data Classification , 2018, 2018 IEEE 3rd International Conference on Cloud Computing and Internet of Things (CCIOT).

[11]  Ridwan Al Iqbal.  Using Feature Weights to Improve Performance of Neural Networks , 2011, ArXiv.

[12]  Matt J. Kusner,et al.  Counterfactual Fairness , 2017, NIPS.

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

[14]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[15]  Lei Zhang,et al.  Ontology-based Clustering Algorithm with Feature Weights , 2010 .

[16]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[17]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[18]  Johannes Gehrke,et al.  Intelligible models for classification and regression , 2012, KDD.

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

[20]  F. Recknagel,et al.  Artificial neural network approach for modelling and prediction of algal blooms , 1997 .

[21]  Nathan Srebro,et al.  Equality of Opportunity in Supervised Learning , 2016, NIPS.

[22]  Johannes Gehrke,et al.  Accurate intelligible models with pairwise interactions , 2013, KDD.

[23]  Been Kim,et al.  Towards A Rigorous Science of Interpretable Machine Learning , 2017, 1702.08608.

[24]  Jun Sakuma,et al.  Fairness-aware Learning through Regularization Approach , 2011, 2011 IEEE 11th International Conference on Data Mining Workshops.

[25]  Ridwan Al Iqbal.  Empirical Learning Aided by Weak Domain Knowledge in the Form of Feature Importance , 2010, 2011 International Conference on Multimedia and Signal Processing.

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

[27]  Toon Calders,et al.  Data preprocessing techniques for classification without discrimination , 2011, Knowledge and Information Systems.