skip to main content

Title: An illustration of model agnostic explainability methods applied to environmental data
Historically, two primary criticisms statisticians have of machine learning and deep neural models is their lack of uncertainty quantification and the inability to do inference (i.e., to explain what inputs are important). Explainable AI has developed in the last few years as a sub‐discipline of computer science and machine learning to mitigate these concerns (as well as concerns of fairness and transparency in deep modeling). In this article, our focus is on explaining which inputs are important in models for predicting environmental data. In particular, we focus on three general methods for explainability that are model agnostic and thus applicable across a breadth of models without internal explainability: “feature shuffling”, “interpretable local surrogates”, and “occlusion analysis”. We describe particular implementations of each of these and illustrate their use with a variety of models, all applied to the problem of long‐lead forecasting monthly soil moisture in the North American corn belt given sea surface temperature anomalies in the Pacific Ocean.  more » « less
Award ID(s):
Author(s) / Creator(s):
; ; ; ; ; ; ; ; ;
Publisher / Repository:
Date Published:
Journal Name:
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract Background

    The expanding usage of complex machine learning methods such as deep learning has led to an explosion in human activity recognition, particularly applied to health. However, complex models which handle private and sometimes protected data, raise concerns about the potential leak of identifiable data. In this work, we focus on the case of a deep network model trained on images of individual faces.

    Materials and methods

    A previously published deep learning model, trained to estimate the gaze from full-face image sequences was stress tested for personal information leakage by a white box inference attack. Full-face video recordings taken from 493 individuals undergoing an eye-tracking- based evaluation of neurological function were used. Outputs, gradients, intermediate layer outputs, loss, and labels were used as inputs for a deep network with an added support vector machine emission layer to recognize membership in the training data.


    The inference attack method and associated mathematical analysis indicate that there is a low likelihood of unintended memorization of facial features in the deep learning model.


    In this study, it is showed that the named model preserves the integrity of training data with reasonable confidence. The same process can be implemented in similar conditions for different models.

    more » « less
  2. Abstract

    With increasing interest in explaining machine learning (ML) models, this paper synthesizes many topics related to ML explainability. We distinguish explainability from interpretability, local from global explainability, and feature importance versus feature relevance. We demonstrate and visualize different explanation methods, how to interpret them, and provide a complete Python package (scikit-explain) to allow future researchers and model developers to explore these explainability methods. The explainability methods include Shapley additive explanations (SHAP), Shapley additive global explanation (SAGE), and accumulated local effects (ALE). Our focus is primarily on Shapley-based techniques, which serve as a unifying framework for various existing methods to enhance model explainability. For example, SHAP unifies methods like local interpretable model-agnostic explanations (LIME) and tree interpreter for local explainability, while SAGE unifies the different variations of permutation importance for global explainability. We provide a short tutorial for explaining ML models using three disparate datasets: a convection-allowing model dataset for severe weather prediction, a nowcasting dataset for subfreezing road surface prediction, and satellite-based data for lightning prediction. In addition, we showcase the adverse effects that correlated features can have on the explainability of a model. Finally, we demonstrate the notion of evaluating model impacts of feature groups instead of individual features. Evaluating the feature groups mitigates the impacts of feature correlations and can provide a more holistic understanding of the model. All code, models, and data used in this study are freely available to accelerate the adoption of machine learning explainability in the atmospheric and other environmental sciences.

    more » « less
  3. As practitioners increasingly deploy machine learning models in critical domains such as health care, finance, and policy, it becomes vital to ensure that domain experts function effectively alongside these models. Explainability is one way to bridge the gap between human decision-makers and machine learning models. However, most of the existing work on explainability focuses on one-off, static explanations like feature importances or rule lists. These sorts of explanations may not be sufficient for many use cases that require dynamic, continuous discovery from stakeholders. In the literature, few works ask decision-makers about the utility of existing explanations and other desiderata they would like to see in an explanation going forward. In this work, we address this gap and carry out a study where we interview doctors, healthcare professionals, and policymakers about their needs and desires for explanations. Our study indicates that decision-makers would strongly prefer interactive explanations in the form of natural language dialogues. Domain experts wish to treat machine learning models as "another colleague", i.e., one who can be held accountable by asking why they made a particular decision through expressive and accessible natural language interactions. Considering these needs, we outline a set of five principles researchers should follow when designing interactive explanations as a starting place for future work. Further, we show why natural language dialogues satisfy these principles and are a desirable way to build interactive explanations. Next, we provide a design of a dialogue system for explainability and discuss the risks, trade-offs, and research opportunities of building these systems. Overall, we hope our work serves as a starting place for researchers and engineers to design interactive explainability systems. 
    more » « less
  4. State-of-the-art industrial-level recommender system applications mostly adopt complicated model structures such as deep neural networks. While this helps with the model performance, the lack of system explainability caused by these nearly blackbox models also raises concerns and potentially weakens the users’ trust in the system. Existing work on explainable recommendation mostly focuses on designing interpretable model structures to generate model-intrinsic explanations. However, most of them have complex structures, and it is difficult to directly apply these designs onto existing recommendation applications due to the effectiveness and efficiency concerns. However, while there have been some studies on explaining recommendation models without knowing their internal structures (i.e., model-agnostic explanations), these methods have been criticized for not reflecting the actual reasoning process of the recommendation model or, in other words, faithfulness . How to develop model-agnostic explanation methods and evaluate them in terms of faithfulness is mostly unknown. In this work, we propose a reusable evaluation pipeline for model-agnostic explainable recommendation. Our pipeline evaluates the quality of model-agnostic explanation from the perspectives of faithfulness and scrutability. We further propose a model-agnostic explanation framework for recommendation and verify it with the proposed evaluation pipeline. Extensive experiments on public datasets demonstrate that our model-agnostic framework is able to generate explanations that are faithful to the recommendation model. We additionally provide quantitative and qualitative study to show that our explanation framework could enhance the scrutability of blackbox recommendation model. With proper modification, our evaluation pipeline and model-agnostic explanation framework could be easily migrated to existing applications. Through this work, we hope to encourage the community to focus more on faithfulness evaluation of explainable recommender systems. 
    more » « less
  5. The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpretable by humans, and how can this be assessed? We focus on two definitions of interpretability that have been introduced in the machine learning literature: simulatability (a user's ability to run a model on a given input) and "what if" local explainability (a user's ability to correctly determine a model's prediction under local changes to the input, given knowledge of the model's original prediction). Through a user study with 1,000 participants, we test whether humans perform well on tasks that mimic the definitions of simulatability and "what if" local explainability on models that are typically considered locally interpretable. To track the relative interpretability of models, we employ a simple metric, the runtime operation count on the simulatability task. We find evidence that as the number of operations increases, participant accuracy on the local interpretability tasks decreases. In addition, this evidence is consistent with the common intuition that decision trees and logistic regression models are interpretable and are more interpretable than neural networks. 
    more » « less