arXiv research

Local surrogate explainers vary in objectives, leading to incomparable explanations.

Proposes MOC method for better counterfactual explanations in ML models.

ADS explains object differences by quantifying and removing underlying properties.

Multi-SpaCE generates valid counterfactual explanations for multivariate time series data.

Attack reveals model details from counterfactual explanations.

Proposes minimal interventions over counterfactual explanations for algorithmic recourse.

Develops causal explanations for black-box classifiers.

This paper proposes a set of criteria to evaluate the objectiveness of explanation methods of neural networks, which is crucial for the development of explainable AI, but it also presents significant challenges. The core challenge is that people usually cannot obtain ground-truth explanations of the neural network. To …

G-SHAP generates multiple types of explanations for machine learning models.

Many methods to explain black-box models, whether local or global, are additive. In this paper, we study global additive explanations for non-additive models, focusing on four explanation methods: partial dependence, Shapley explanations adapted to a global setting, distilled additive explanations, and gradient-based e…

We consider objective evaluation measures of saliency explanations for complex black-box machine learning models. We propose simple robust variants of two notions that have been considered in recent literature: (in)fidelity, and sensitivity. We analyze optimal explanations with respect to both these measures, and while…

Proposes counterfactual explanations for deep two-sample tests on high-dimensional data.

GRANITE unifies feature-based explanation methods to reduce disagreement.

Paper compares two local explanation methods for machine learning models.

Proposes an efficient method for ordered counterfactual explanations.

New method identifies differences between groups in low-dimensional data representations.

AXE evaluates explanations to avoid misleading Rashomon set model selection.

The paper introduces metrics to objectively evaluate interpretability methods.

In this paper we address three main objections of behavioral finance to the theory of rational finance, considered as anomalies the theory of rational finance cannot explain: Predictability of asset returns, The Equity Premium, (The Volatility Puzzle. We offer resolutions of those objections within the rational finance…

For an explanation of a deep learning model to be effective, it must provide both insight into a model and suggest a corresponding action in order to achieve some objective. Too often, the litany of proposed explainable deep learning methods stop at the first step, providing practitioners with insight into a model, but…

Recent work in model-agnostic explanations of black-box machine learning has demonstrated that interpretability of complex models does not have to come at the cost of accuracy or model flexibility. However, it is not clear what kind of explanations, such as linear models, decision trees, and rule lists, are the appropr…

FeAT improves OOD generalization by learning richer features.

COMRECGC finds common recourse for global counterfactual explanations in GNNs.

New method evaluates visual explanations of deep models using adversarial perturbations.

New research challenges the idea that counterfactual explanations should be sparse.

Due to the increasing use of machine learning in practice it becomes more and more important to be able to explain the prediction and behavior of machine learning models. An instance of explanations are counterfactual explanations which provide an intuitive and useful explanations of machine learning models. In this su…

Ordinal regression predicts the objects' labels that exhibit a natural ordering, which is important to many managerial problems such as credit scoring and clinical diagnosis. In these problems, the ability to explain how the attributes affect the prediction is critical to users. However, most, if not all, existing ordi…

Proposes a model for generating survival trajectories and data.

RAW-Explainer generates interpretable subgraph explanations for link predictions in knowledge graphs.

Many proposed methods for explaining machine learning predictions are in fact challenging to understand for nontechnical consumers. This paper builds upon an alternative consumer-driven approach called TED that asks for explanations to be provided in training data, along with target labels. Using semi-synthetic data fr…

Managing large-scale transportation infrastructure projects is difficult due to frequent misinformation about the costs which results in large cost overruns that often threaten the overall project viability. This paper investigates the explanations for cost overruns that are given in the literature. Overall, four categ…

Interpretability is an elusive but highly sought-after characteristic of modern machine learning methods. Recent work has focused on interpretability via $\textit{explanations}$, which justify individual model predictions. In this work, we take a step towards reconciling machine explanations with those that humans prod…

Introduces PCG for better counterfactual explanations in vision models.

Unified framework for feature-based explanations using ANOVA and game theory.

Interpretation and explanation of deep models is critical towards wide adoption of systems that rely on them. In this paper, we propose a novel scheme for both interpretation as well as explanation in which, given a pretrained model, we automatically identify internal features relevant for the set of classes considered…

Develops transparent global models consistent with local explanations.

Explearn learns to explain predictions using Gaussian Processes.

R package for counterfactual explanation methods.

This research examines how model explanations change under distribution shifts in tabular data.

In the past years, many new explanation methods have been proposed to achieve interpretability of machine learning predictions. However, the utility of these methods in practical applications has not been researched extensively. In this paper we present the results of a human-grounded evaluation of SHAP, an explanation…

Interpretable Machine Learning (IML) has become increasingly important in many real-world applications, such as autonomous cars and medical diagnosis, where explanations are significantly preferred to help people better understand how machine learning systems work and further enhance their trust towards systems. Howeve…

GraphOpt learns the formation mechanism of graphs from observed structures.

We introduce a new model-agnostic explanation technique which explains the prediction of any classifier called CLE. CLE gives an faithful and interpretable explanation to the prediction, by approximating the model locally using an interpretable model. We demonstrate the flexibility of CLE by explaining different models…

OrphicX generates causal explanations for GNNs by isolating latent causal factors.

The paper tackles strategic behavior in decision-making with counterfactual explanations.

Black-box explanation is the problem of explaining how a machine learning model -- whose internal logic is hidden to the auditor and generally complex -- produces its outcomes. Current approaches for solving this problem include model explanation, outcome explanation as well as model inspection. While these techniques …

Local Interpretable Model-Agnostic Explanations (LIME) is a popular technique used to increase the interpretability and explainability of black box Machine Learning (ML) algorithms. LIME typically generates an explanation for a single prediction by any ML model by learning a simpler interpretable model (e.g. linear cla…

Explainable recommendation is far from being well solved partly due to three challenges. The first is the personalization of preference learning, which requires that different items/users have different contributions to the learning of user preference or item quality. The second one is dynamic explanation, which is cru…