Calibrated Explanations is a recently proposed feature importance explanation method providing uncertainty quantification. It utilises Venn-Abers to generate well-calibrated factual and counterfactual explanations for binary classification. In this paper, we extend the method to support multi-class classification. The paper includes an evaluation illustrating the calibration quality of the selected multi-class calibration approach, as well as a demonstration of how the explanations can help determine which explanations to trust.

While local explanations for AI models can offer insights into individual predictions, such as feature importance, they are plagued by issues like instability. The unreliability of feature weights, often skewed due to poorly calibrated ML models, deepens these challenges. Moreover, the critical aspect of feature importance uncertainty remains mostly unaddressed in Explainable AI (XAI). The novel feature importance explanation method presented in this paper, called Calibrated Explanations (CE), is designed to tackle these issues head-on. Built on the foundation of Venn-Abers, CE not only calibrates the underlying model but also delivers reliable feature importance explanations with an exact definition of the feature weights. CE goes beyond conventional solutions by addressing output uncertainty. It accomplishes this by providing uncertainty quantification for both feature weights and the model’s probability estimates. Additionally, CE is model-agnostic, featuring easily comprehensible conditional rules and the ability to generate counterfactual explanations with embedded uncertainty quantification. Results from an evaluation with 25 benchmark datasets underscore the efficacy of CE, making it stand as a fast, reliable, stable, and robust solution.

While Artificial Intelligence and Machine Learning models are becoming increasingly prevalent, it is essential to remember that they are not infallible or inherently objective. These models depend on the data they are trained on and the inherent bias of the chosen machine learning algorithm. Therefore, selecting and sampling data for training is crucial for a fair outcome of the model. A model predicting, e.g., whether an applicant should be taken further in the job application process, could create heavily biased predictions against women if the data used to train the model mostly contained information about men. The well-known concept of conditional categories used in Conformal Prediction can be utilised to address this type of bias in the data. The Conformal Prediction framework includes uncertainty quantification methods for classification and regression. To help meet the challenges of data sets with potential bias, conditional categories were incorporated into an existing explanation method called Calibrated Explanations, relying on conformal methods. This approach allows users to try out different settings while simultaneously having the possibility to study how the uncertainty in the predictions is affected on an individual level. Furthermore, this paper evaluated how the uncertainty changed when using conditional categories based on attributes containing potential bias. It showed that the uncertainty significantly increased, revealing that fairness came with a cost of increased uncertainty.

Automatic recognition of grocery products can be used to improve customer flow at checkouts and reduce labor costs and store losses. Product recognition is, however, a challenging task for machine learning-based solutions due to the large number of products and their variations in appearance. In this work, we tackle the challenge of fine-grained product recognition by first extracting a large dataset from a grocery store containing products that are only differentiable by subtle details. Then, we propose a multimodal product recognition approach that uses product images with extracted OCR text from packages to improve fine-grained recognition of grocery products. We evaluate several image and text models separately and then combine them using different multimodal models of varying complexities. The results show that image and textual information complement each other in multimodal models and enable a classifier with greater recognition performance than unimodal models, especially when the number of training samples is limited. Therefore, this approach is suitable for many different scenarios in which product recognition is used to further improve recognition performance. The dataset can be found at https://github.com/Tubbias/finegrainocr.

Applying conformal prediction in real-world industrial use cases is rare, and publications are often limited to popular open-source data sets. This paper demonstrates two experimental use cases where the conformal prediction framework was applied to regression problems at Husqvarna Group with the two Python-based open-source platforms MAPIE and Crepes. The paper concludes by discussing lessons learned for the industry and some challenges for the conformal prediction community to address.

In many situations, probabilistic predictors have replaced conformal classifiers. The main reason is arguably that the set predictions of conformal classifiers, with the accompanying significance level, are hard to interpret. In this paper, we demonstrate how conformal classification can be used as a basis for a classifier with reject option. Specifically, we introduce and evaluate two algorithms that are able to perfectly estimate accuracy or precision for a set of test instances, in a classifier with reject scenario. In the empirical investigation, the suggested algorithms are shown to clearly outperform both calibrated and uncalibrated probabilistic predictors.

A standard classifier is forced to predict the label of every test instance, even when confidence in the predictions is very low. In many scenarios, it would, however, be better to avoid making these predictions, maybe leaving them to a human expert. A classifier with that alternative is referred to as a classifier with reject option. In this paper, we propose an algorithm that, for a particular data set, automatically suggests a number of accuracy levels, which it will be able to meet perfectly, using a classifier with reject option. Since the basis of the suggested algorithm is conformal prediction, it comes with strong validity guarantees. The experimentation, using 25 publicly available two-class data sets, confirms that the algorithm obtains empirical accuracies very close to the requested levels. In addition, in an outright comparison with probabilistic predictors, including models calibrated with Platt scaling, the suggested algorithm clearly outperforms the alternatives.

Being able to understand the logic behind predictions or recommendations on the instance level is at the heart of trustworthy machine learning models. Inherently interpretable models make this possible by allowing inspection and analysis of the model itself, thus exhibiting the logic behind each prediction, while providing an opportunity to gain insights about the underlying domain. Another important criterion for trustworthiness is the model’s ability to somehow communicate a measure of confidence in every specific prediction or recommendation. Indeed, the overall goal of this paper is to produce highly informative models that combine interpretability and algorithmic confidence. For this purpose, we introduce conformal predictive distribution trees, which is a novel form of regression trees where each leaf contains a conformal predictive distribution. Using this representation language, the proposed approach allows very versatile analyses of individual leaves in the regression trees. Specifically, depending on the chosen level of detail, the leaves, in addition to the normal point predictions, can provide either cumulative distributions or prediction intervals that are guaranteed to be well-calibrated. In the empirical evaluation, the suggested conformal predictive distribution trees are compared to the well-established conformal regressors, thus demonstrating the benefits of the enhanced representation.

Grocery product recognition techniques are emerging in the retail sector and are used to provide automatic checkout counters, reduce self-checkout fraud, and support inventory management. However, recognizing grocery products using machine learning models is challenging due to the vast number of products, their similarities, and changes in appearance. To address these challenges, more complex models are created by adding additional modalities, such as text from product packages. But these complex models pose additional challenges in terms of model interpretability. Machine learning experts and system developers need tools and techniques conveying interpretations to enable the evaluation and improvement of multimodal production recognition models.

In this work, we propose thus an approach to provide local and global explanations that allow us to assess multimodal models for product recognition. We evaluate this approach on a large fine-grained grocery product dataset captured from a real-world environment. To assess the utility of our approach, experiments are conducted for three types of multimodal models.

The results show that our approach provides fine-grained local explanations while being able to aggregate those into global explanations for each type of product. In addition, we observe a disparity between different multimodal models, in what type of features they learn and what modality each model focuses on. This provides valuable insight to further improve the accuracy and robustness of multimodal product recognition models for grocery product recognition.

Predictive models used in Decision Support Systems (DSS) are often requested to explain the reasoning to users. Explanations of instances consist of two parts; the predicted label with an associated certainty and a set of weights, one per feature, describing how each feature contributes to the prediction for the particular instance. In techniques like Local Interpretable Model-agnostic Explanations (LIME), the probability estimate from the underlying model is used as a measurement of certainty; consequently, the feature weights represent how each feature contributes to the probability estimate. It is, however, well-known that probability estimates from classifiers are often poorly calibrated, i.e., the probability estimates do not correspond to the actual probabilities of being correct. With this in mind, explanations from techniques like LIME risk becoming misleading since the feature weights will only describe how each feature contributes to the possibly inaccurate probability estimate. This paper investigates the impact of calibrating predictive models before applying LIME. The study includes 25 benchmark data sets, using Random forest and Extreme Gradient Boosting (xGBoost) as learners and Venn-Abers and Platt scaling as calibration methods. Results from the study show that explanations of better calibrated models are themselves better calibrated, with ECE and log loss for the explanations after calibration becoming more conformed to the model ECE and log loss. The conclusion is that calibration makes the models and the explanations better by accurately representing reality.