Automated Dependence Plots

Abstract

In practical applications of machine learning, it is necessary to look beyond standard metrics such as test accuracy in order to validate various qualitative properties of a model. Partial dependence plots (PDP), including instance-specific PDPs (i.e., ICE plots), have been widely used as a visual tool to understand or validate a model. Yet, current PDPs suffer from two main drawbacks: (1) a user must manually sort or select interesting plots, and (2) PDPs are usually limited to plots along a single feature. To address these drawbacks, we formalize a method for automating the selection of interesting PDPs and extend PDPs beyond showing single features to show the model response along arbitrary directions, for example in raw feature space or a latent space arising from some generative model. We demonstrate the usefulness of our automated dependence plots (ADP) across multiple use-cases and datasets including model selection, bias detection, understanding out-of-sample behavior, and exploring the latent space of a generative model.

In Uncertainty in Artificial Intelligence (UAI 2020). Camera-ready version. Code is available at https://github.com/davidinouye/adp

References in corpus (13)

• Auto-Encoding Variational Bayes
• Axiomatic Attribution for Deep Networks
• Learning Important Features Through Propagating Activation Differences
• Understanding Black-box Predictions via Influence Functions
• SmoothGrad: removing noise by adding noise
• The What-If Tool: Interactive Probing of Machine Learning Models
• MADE: Masked Autoencoder for Distribution Estimation
• Local Rule-Based Explanations of Black Box Decision Systems
• Representer Point Selection for Explaining Deep Neural Networks
• Tutorial: Safe and Reliable Machine Learning
• Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections
• Fairer and more accurate, but for whom?
• Explaining Deep Learning Models - A Bayesian Non-parametric Approach