Brian Barr

Peter Xenopoulos, Joao Rulff, Luis Gustavo Nonato et al.

Analyzing classification model performance is a crucial task for machine learning practitioners. While practitioners often use count-based metrics derived from confusion matrices, like accuracy, many applications, such as weather prediction, sports betting, or patient risk prediction, rely on a classifier's predicted probabilities rather than predicted labels. In these instances, practitioners are concerned with producing a calibrated model, that is, one which outputs probabilities that reflect those of the true distribution. Model calibration is often analyzed visually, through static reliability diagrams, however, the traditional calibration visualization may suffer from a variety of drawbacks due to the strong aggregations it necessitates. Furthermore, count-based approaches are unable to sufficiently analyze model calibration. We present Calibrate, an interactive reliability diagram that addresses the aforementioned issues. Calibrate constructs a reliability diagram that is resistant to drawbacks in traditional approaches, and allows for interactive subgroup analysis and instance-level inspection. We demonstrate the utility of Calibrate through use cases on both real-world and synthetic data. We further validate Calibrate by presenting the results of a think-aloud experiment with data scientists who routinely analyze model calibration.

Isha Hameed, Samuel Sharpe, Daniel Barcklow et al.

Explainable artificial intelligence (XAI) methods lack ground truth. In its place, method developers have relied on axioms to determine desirable properties for their explanations' behavior. For high stakes uses of machine learning that require explainability, it is not sufficient to rely on axioms as the implementation, or its usage, can fail to live up to the ideal. As a result, there exists active research on validating the performance of XAI methods. The need for validation is especially magnified in domains with a reliance on XAI. A procedure frequently used to assess their utility, and to some extent their fidelity, is an ablation study. By perturbing the input variables in rank order of importance, the goal is to assess the sensitivity of the model's performance. Perturbing important variables should correlate with larger decreases in measures of model capability than perturbing less important features. While the intent is clear, the actual implementation details have not been studied rigorously for tabular data. Using five datasets, three XAI methods, four baselines, and three perturbations, we aim to show 1) how varying perturbations and adding simple guardrails can help to avoid potentially flawed conclusions, 2) how treatment of categorical variables is an important consideration in both post-hoc explainability and ablation studies, and 3) how to identify useful baselines for XAI methods and viable perturbations for ablation studies.

Brian Barr, Noah Fatsi, Leif Hancox-Li et al.

The field of explainable artificial intelligence (XAI) aims to explain how black-box machine learning models work. Much of the work centers around the holy grail of providing post-hoc feature attributions to any model architecture. While the pace of innovation around novel methods has slowed down, the question remains of how to choose a method, and how to make it fit for purpose. Recently, efforts around benchmarking XAI methods have suggested metrics for that purpose -- but there are many choices. That bounty of choice still leaves an end user unclear on how to proceed. This paper focuses on comparing metrics with the aim of measuring faithfulness of local explanations on tabular classification problems -- and shows that the current metrics don't agree; leaving users unsure how to choose the most faithful explanations.

Wei Zhang, Brian Barr, John Paisley

Deep neural networks have revolutionized many fields, but their black-box nature also occasionally prevents their wider adoption in fields such as healthcare and finance, where interpretable and explainable models are required. The recent development of Neural Additive Models (NAMs) is a significant step in the direction of interpretable deep learning for tabular datasets. In this paper, we propose a new subclass of NAMs that use a single-layer neural network construction of the Gaussian process via random Fourier features, which we call Gaussian Process Neural Additive Models (GP-NAM). GP-NAMs have the advantage of a convex objective function and number of trainable parameters that grows linearly with feature dimensionality. It suffers no loss in performance compared to deeper NAM approaches because GPs are well-suited for learning complex non-parametric univariate functions. We demonstrate the performance of GP-NAM on several tabular datasets, showing that it achieves comparable or better performance in both classification and regression tasks with a large reduction in the number of parameters.

Evandro S. Ortigossa, Fábio F. Dias, Brian Barr et al.

The development of machine learning applications has increased significantly in recent years, motivated by the remarkable ability of learning-powered systems to discover and generalize intricate patterns hidden in massive datasets. Modern learning models, while powerful, often exhibit a complexity level that renders them opaque black boxes, lacking transparency and hindering our understanding of their decision-making processes. Opacity challenges the practical application of machine learning, especially in critical domains requiring informed decisions. Explainable Artificial Intelligence (XAI) addresses that challenge, unraveling the complexity of black boxes by providing explanations. Feature attribution/importance XAI stands out for its ability to delineate the significance of input features in predictions. However, most attribution methods have limitations, such as instability, when divergent explanations result from similar or the same instance. This work introduces T-Explainer, a novel additive attribution explainer based on the Taylor expansion that offers desirable properties such as local accuracy and consistency. We demonstrate T-Explainer's effectiveness and stability over multiple runs in quantitative benchmark experiments against well-known attribution methods. Additionally, we provide several tools to evaluate and visualize explanations, turning T-Explainer into a comprehensive XAI framework.

Wei Zhang, Brian Barr, John Paisley

Explainable machine learning has attracted much interest in the community where the stakes are high. Counterfactual explanations methods have become an important tool in explaining a black-box model. The recent advances have leveraged the power of generative models such as an autoencoder. In this paper, we propose a novel method using a Gaussian process to construct the auto-encoder architecture for generating counterfactual samples. The resulting model requires fewer learnable parameters and thus is less prone to overfitting. We also introduce a novel density estimator that allows for searching for in-distribution samples. Furthermore, we introduce an algorithm for selecting the optimal regularization rate on density estimator while searching for counterfactuals. We experiment with our method in several large-scale tabular datasets and compare with other auto-encoder-based methods. The results show that our method is capable of generating diversified and in-distribution counterfactual samples.

Wei Zhang, Brian Barr, John Paisley

Counterfactual explanations methods provide an important tool in the field of {interpretable machine learning}. Recent advances in this direction have focused on diffusion models to explain a deep classifier. However, these techniques have predominantly focused on problems in computer vision. In this paper, we focus on tabular data typical in finance and the social sciences and propose a novel guided reverse process for categorical features based on an approximation to the Gumbel-softmax distribution. Furthermore, we study the effect of the temperature $τ$ and derive a theoretical bound between the Gumbel-softmax distribution and our proposed approximated distribution. We perform experiments on several large-scale credit lending and other tabular datasets, assessing their performance in terms of the quantitative measures of interpretability, diversity, instability, and validity. These results indicate that our approach outperforms popular baseline methods, producing robust and realistic counterfactual explanations.

John Paisley, Ghazal Fazelnia, Brian Barr

We exploit the observation that stochastic variational inference (SVI) is a form of annealing and present a modified SVI approach -- applicable to both large and small datasets -- that allows the amount of annealing done by SVI to be tuned. We are motivated by the fact that, in SVI, the larger the batch size the more approximately Gaussian is the noise of the gradient, but the smaller its variance, which reduces the amount of annealing done to escape bad local optimal solutions. We propose a simple method for achieving both goals of having larger variance noise to escape bad local optimal solutions and more data information to obtain more accurate gradient directions. The idea is to set an actual batch size, which may be the size of the data set, and an effective batch size that matches the increased variance of a smaller batch size. The result is an approximation to the maximum entropy stochastic gradient at a desired variance level. We theoretically motivate our ``SVI+'' approach for conjugate exponential family model framework and illustrate its empirical performance for learning the probabilistic matrix factorization collaborative filter (PMF), the Latent Dirichlet Allocation topic model (LDA), and the Gaussian mixture model (GMM).

John Paisley, Wei Zhang, Brian Barr

We propose a nonparametric density estimator based on the Gaussian process (GP) and derive three novel closed form learning algorithms based on Fisher divergence (FD) score matching. The density estimator is formed by multiplying a base multivariate normal distribution with an exponentiated GP refinement, and so we refer to it as a GP-tilted nonparametric density. By representing the GP part of the score as a linear function using the random Fourier feature (RFF) approximation, we show that optimization can be solved in closed form for the three FD-based objectives considered. This includes the basic and noise conditional versions of the Fisher divergence, as well as an alternative to noise conditional FD models based on variational inference (VI) that we propose in this paper. For this novel learning approach, we propose an ELBO-like optimization to approximate the posterior distribution, with which we then derive a Fisher variational predictive distribution. The RFF representation of the GP, which is functionally equivalent to a single layer neural network score model with cosine activation, provides a useful linear representation of the GP for which all expectations can be solved. The Gaussian base distribution also helps with tractability of the VI approximation and ensures that our proposed density is well-defined. We demonstrate our three learning algorithms, as well as a MAP baseline algorithm, on several low dimensional density estimation problems. The closed form nature of the learning problem removes the reliance on iterative learning algorithms, making this technique particularly well-suited to big data sets, since only sufficient statistics collected from a single pass through the data is needed.

Parikshit Solunke, Vitoria Guardieiro, Joao Rulff et al.

With the increasing use of black-box Machine Learning (ML) techniques in critical applications, there is a growing demand for methods that can provide transparency and accountability for model predictions. As a result, a large number of local explainability methods for black-box models have been developed and popularized. However, machine learning explanations are still hard to evaluate and compare due to the high dimensionality, heterogeneous representations, varying scales, and stochastic nature of some of these methods. Topological Data Analysis (TDA) can be an effective method in this domain since it can be used to transform attributions into uniform graph representations, providing a common ground for comparison across different explanation methods. We present a novel topology-driven visual analytics tool, Mountaineer, that allows ML practitioners to interactively analyze and compare these representations by linking the topological graphs back to the original data distribution, model predictions, and feature attributions. Mountaineer facilitates rapid and iterative exploration of ML explanations, enabling experts to gain deeper insights into the explanation techniques, understand the underlying data distributions, and thus reach well-founded conclusions about model behavior. Furthermore, we demonstrate the utility of Mountaineer through two case studies using real-world data. In the first, we show how Mountaineer enabled us to compare black-box ML explanations and discern regions of and causes of disagreements between different explanations. In the second, we demonstrate how the tool can be used to compare and understand ML models themselves. Finally, we conducted interviews with three industry experts to help us evaluate our work.

Jun Yuan, Brian Barr, Kyle Overton et al.

One of the potential solutions for model interpretation is to train a surrogate model: a more transparent model that approximates the behavior of the model to be explained. Typically, classification rules or decision trees are used due to the intelligibility of their logic-based expressions. However, decision trees can grow too deep and rule sets can become too large to approximate a complex model. Unlike paths on a decision tree that must share ancestor nodes (conditions), rules are more flexible. However, the unstructured visual representation of rules makes it hard to make inferences across rules. To address these issues, we present a workflow that includes novel algorithmic and interactive solutions. First, we present Hierarchical Surrogate Rules (HSR), an algorithm that generates hierarchical rules based on user-defined parameters. We also contribute SuRE, a visual analytics (VA) system that integrates HSR and interactive surrogate rule visualizations. Particularly, we present a novel feature-aligned tree to overcome the shortcomings of existing rule visualizations. We evaluate the algorithm in terms of parameter sensitivity, time performance, and comparison with surrogate decision trees and find that it scales reasonably well and outperforms decision trees in many respects. We also evaluate the visualization and the VA system by a usability study with 24 volunteers and an observational study with 7 domain experts. Our investigation shows that the participants can use feature-aligned trees to perform non-trivial tasks with very high accuracy. We also discuss many interesting observations that can be useful for future research on designing effective rule-based VA systems.

Peter Xenopoulos, Gromit Chan, Harish Doraiswamy et al.

Local explainability methods -- those which seek to generate an explanation for each prediction -- are becoming increasingly prevalent due to the need for practitioners to rationalize their model outputs. However, comparing local explainability methods is difficult since they each generate outputs in various scales and dimensions. Furthermore, due to the stochastic nature of some explainability methods, it is possible for different runs of a method to produce contradictory explanations for a given observation. In this paper, we propose a topology-based framework to extract a simplified representation from a set of local explanations. We do so by first modeling the relationship between the explanation space and the model predictions as a scalar function. Then, we compute the topological skeleton of this function. This topological skeleton acts as a signature for such functions, which we use to compare different explanation methods. We demonstrate that our framework can not only reliably identify differences between explainability techniques but also provides stable representations. Then, we show how our framework can be used to identify appropriate parameters for local explainability methods. Our framework is simple, does not require complex optimizations, and can be broadly applied to most local explanation methods. We believe the practicality and versatility of our approach will help promote topology-based approaches as a tool for understanding and comparing explanation methods.

Brian Barr, Matthew R. Harrington, Samuel Sharpe et al.

Counterfactual explanations represent the minimal change to a data sample that alters its predicted classification, typically from an unfavorable initial class to a desired target class. Counterfactuals help answer questions such as "what needs to change for this application to get accepted for a loan?". A number of recently proposed approaches to counterfactual generation give varying definitions of "plausible" counterfactuals and methods to generate them. However, many of these methods are computationally intensive and provide unconvincing explanations. Here we introduce SharpShooter, a method for binary classification that starts by creating a projected version of the input that classifies as the target class. Counterfactual candidates are then generated in latent space on the interpolation line between the input and its projection. We then demonstrate that our framework translates core characteristics of a sample to its counterfactual through the use of learned representations. Furthermore, we show that SharpShooter is competitive across common quality metrics on tabular and image datasets while being orders of magnitude faster than two comparable methods and excels at measures of realism, making it well-suited for high velocity machine learning applications which require timely explanations.

Rachana Balasubramanian, Samuel Sharpe, Brian Barr et al.

In the environment of fair lending laws and the General Data Protection Regulation (GDPR), the ability to explain a model's prediction is of paramount importance. High quality explanations are the first step in assessing fairness. Counterfactuals are valuable tools for explainability. They provide actionable, comprehensible explanations for the individual who is subject to decisions made from the prediction. It is important to find a baseline for producing them. We propose a simple method for generating counterfactuals by using gradient descent to search in the latent space of an autoencoder and benchmark our method against approaches that search for counterfactuals in feature space. Additionally, we implement metrics to concretely evaluate the quality of the counterfactuals. We show that latent space counterfactual generation strikes a balance between the speed of basic feature gradient descent methods and the sparseness and authenticity of counterfactuals generated by more complex feature space oriented techniques.

Gromit Yeuk-Yin Chan, Enrico Bertini, Luis Gustavo Nonato et al.

With the increasing sophistication of machine learning models, there are growing trends of developing model explanation techniques that focus on only one instance (local explanation) to ensure faithfulness to the original model. While these techniques provide accurate model interpretability on various data primitive (e.g., tabular, image, or text), a holistic Explainable Artificial Intelligence (XAI) experience also requires a global explanation of the model and dataset to enable sensemaking in different granularity. Thus, there is a vast potential in synergizing the model explanation and visual analytics approaches. In this paper, we present MELODY, an interactive algorithm to construct an optimal global overview of the model and data behavior by summarizing the local explanations using information theory. The result (i.e., an explanation summary) does not require additional learning models, restrictions of data primitives, or the knowledge of machine learning from the users. We also design MELODY UI, an interactive visual analytics system to demonstrate how the explanation summary connects the dots in various XAI tasks from a global overview to local inspections. We present three usage scenarios regarding tabular, image, and text classifications to illustrate how to generalize model interpretability of different data. Our experiments show that our approaches: (1) provides a better explanation summary compared to a straightforward information-theoretic summarization and (2) achieves a significant speedup in the end-to-end data modeling pipeline.

Jun Yuan, Gromit Yeuk-Yin Chan, Brian Barr et al.

Understanding the interpretation of machine learning (ML) models has been of paramount importance when making decisions with societal impacts such as transport control, financial activities, and medical diagnosis. While current model interpretation methodologies focus on using locally linear functions to approximate the models or creating self-explanatory models that give explanations to each input instance, they do not focus on model interpretation at the subpopulation level, which is the understanding of model interpretations across different subset aggregations in a dataset. To address the challenges of providing explanations of an ML model across the whole dataset, we propose SUBPLEX, a visual analytics system to help users understand black-box model explanations with subpopulation visual analysis. SUBPLEX is designed through an iterative design process with machine learning researchers to address three usage scenarios of real-life machine learning tasks: model debugging, feature selection, and bias detection. The system applies novel subpopulation analysis on ML model explanations and interactive visualization to explore the explanations on a dataset with different levels of granularity. Based on the system, we conduct user evaluation to assess how understanding the interpretation at a subpopulation level influences the sense-making process of interpreting ML models from a user's perspective. Our results suggest that by providing model explanations for different groups of data, SUBPLEX encourages users to generate more ingenious ideas to enrich the interpretations. It also helps users to acquire a tight integration between programming workflow and visual analytics workflow. Last but not least, we summarize the considerations observed in applying visualization to machine learning interpretations.

Brian Barr, Ke Xu, Claudio Silva et al.

In data science, there is a long history of using synthetic data for method development, feature selection and feature engineering. Our current interest in synthetic data comes from recent work in explainability. Today's datasets are typically larger and more complex - requiring less interpretable models. In the setting of \textit{post hoc} explainability, there is no ground truth for explanations. Inspired by recent work in explaining image classifiers that does provide ground truth, we propose a similar solution for tabular data. Using copulas, a concise specification of the desired statistical properties of a dataset, users can build intuition around explainability using controlled data sets and experimentation. The current capabilities are demonstrated on three use cases: one dimensional logistic regression, impact of correlation from informative features, impact of correlation from redundant variables.