Related papers: An Imprecise SHAP as a Tool for Explaining the Cla…
Although Shapley additive explanations (SHAP) can be computed in polynomial time for simple models like decision trees, they unfortunately become NP-hard to compute for more expressive black-box models like neural networks - where…
With the adoption of machine learning into routine clinical practice comes the need for Explainable AI methods tailored to medical applications. Shapley values have sparked wide interest for locally explaining models. Here, we demonstrate…
Iterative Closest Point (ICP) is a commonly used algorithm to estimate transformation between two point clouds. The key idea of this work is to leverage recent advances in explainable AI for probabilistic ICP methods that provide…
We introduce a new Shapley value approach for global sensitivity analysis and machine learning explainability. The method is based on the first-order partial derivatives of the underlying function. The computational complexity of the method…
Shapley value attribution (SVA) is an increasingly popular explainable AI (XAI) method, which quantifies the contribution of each feature to the model's output. However, recent work has shown that most existing methods to implement SVAs…
Feature attribution for kernel methods is often heuristic and not individualised for each prediction. To address this, we turn to the concept of Shapley values~(SV), a coalition game theoretical framework that has previously been applied to…
Even though Shapley value provides an effective explanation for a DNN model prediction, the computation relies on the enumeration of all possible input feature coalitions, which leads to the exponentially growing complexity. To address this…
Feature attributions are a common paradigm for model explanations due to their simplicity in assigning a single numeric score for each input feature to a model. In the actionable recourse setting, wherein the goal of the explanations is to…
In this work, we examine Asymmetric Shapley Values (ASV), a variant of the popular SHAP additive local explanation method. ASV proposes a way to improve model explanations incorporating known causal relations between variables, and is also…
Interpretability is central for scientific machine learning, as understanding \emph{why} models make predictions enables hypothesis generation and validation. While tabular foundation models show strong performance, existing explanation…
Probabilistic graphical models, such as Markov random fields (MRF), exploit dependencies among random variables to model a rich family of joint probability distributions. Sophisticated inference algorithms, such as belief propagation (BP),…
In recent years, machine learning models have been increasingly applied to spectroscopic datasets for chemical and biomedical analysis. For their successful adoption, particularly in clinical and safety-critical settings, professionals and…
The problem of explaining the behavior of deep neural networks has recently gained a lot of attention. While several attribution methods have been proposed, most come without strong theoretical foundations, which raises questions about…
Shapley value is a classic notion from game theory, historically used to quantify the contributions of individuals within groups, and more recently applied to assign values to data points when training machine learning models. Despite its…
Multimodal learning combines information from multiple data modalities to improve predictive performance. However, modalities often contribute unequally and in a data dependent way, making it unclear which data modalities are genuinely…
For around a decade, non-symbolic methods have been the option of choice when explaining complex machine learning (ML) models. Unfortunately, such methods lack rigor and can mislead human decision-makers. In high-stakes uses of ML, the lack…
Data Shapley provides a principled framework for attributing data's contribution within machine learning contexts. However, existing approaches require re-training models on different data subsets, which is computationally intensive,…
We study instancewise feature importance scoring as a method for model interpretation. Any such method yields, for each predicted instance, a vector of importance scores associated with the feature vector. Methods based on the Shapley score…
This paper presents a conformal prediction method for classification in highly imbalanced and open-set settings, where there are many possible classes and not all may be represented in the data. Existing approaches require a finite, known…
This paper introduces the shapr R package, a versatile tool for generating Shapley value-based prediction explanations for machine learning and statistical regression models. Moreover, the shaprpy Python library brings the core capabilities…