Toward Explainable AI for Regression Models

Abstract

In addition to the impressive predictive power of machine learning (ML) models, more recently, explanation methods have emerged that enable an interpretation of complex non-linear learning models such as deep neural networks. Gaining a better understanding is especially important e.g. for safety-critical ML applications or medical diagnostics etc. While such Explainable AI (XAI) techniques have reached significant popularity for classifiers, so far little attention has been devoted to XAI for regression models (XAIR). In this review, we clarify the fundamental conceptual differences of XAI for regression and classification tasks, establish novel theoretical insights and analysis for XAIR, provide demonstrations of XAIR on genuine practical regression problems, and finally discuss the challenges remaining for the field.

arXiv comment17 pages, 10 figures, published; changes: 1. references to code and xai-regression.org added (p. 1/2, end of introduction), 2. adjustment of sign-error in restructuring section (p. 8, just above Fig. 4)

References in corpus (35)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Axiomatic Attribution for Deep Networks
• Methods for Interpreting and Understanding Deep Neural Networks
• Striving for Simplicity: The All Convolutional Net
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• SchNet - a deep learning architecture for molecules and materials
• Machine Learning Force Fields
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Explainable Machine Learning for Scientific Insights and Discoveries
• Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
• Machine learning for molecular simulation
• A Unifying Review of Deep and Shallow Anomaly Detection
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• How to Explain Individual Classification Decisions
• GNNExplainer: Generating Explanations for Graph Neural Networks
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Directional Message Passing for Molecular Graphs
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks
• Explanations can be manipulated and geometry is to blame
• NeuralHydrology -- Interpreting LSTMs in Hydrology
• Explaining by Removing: A Unified Framework for Model Explanation
• Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey
• From Clustering to Cluster Explanations via Neural Networks
• Towards Explaining Anomalies: A Deep Taylor Decomposition of One-Class Models
• Explaining and Interpreting LSTMs
• Building and Interpreting Deep Similarity Models
• Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy
• Age and Gender Prediction From Face Images Using Attentional Convolutional Network
• Counterfactual Explanations for Arbitrary Regression Models

Cited by in corpus (7)

• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• A Survey and Comparison of Post-quantum and Quantum Blockchains
• An XAI framework for robust and transparent data-driven wind turbine power curve models
• PredDiff: Explanations and Interactions from Conditional Expectations
• Calibrated Explanations for Regression
• Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks
• Decoding the human brain tissue response to radiofrequency excitation using a biophysical-model-free deep MRI on a chip framework