English
Related papers

Related papers: Inferring feature importance with uncertainties in…

200 papers

A key task of data science is to identify relevant features linked to certain output variables that are supposed to be modeled or predicted. To obtain a small but meaningful model, it is important to find stochastically independent…

Methodology · Statistics 2021-12-23 Tim Breitenbach , Lauritz Rasbach , Chunguang Liang , Patrick Jahnke

Foundation models have become a dominant paradigm in machine learning, achieving remarkable performance across diverse tasks through large-scale pretraining. However, these models often yield overconfident, uncalibrated predictions. The…

Machine Learning · Computer Science 2026-01-30 Mehmet Ozgur Turkoglu , Dominik J. Mühlematter , Alexander Becker , Konrad Schindler , Helge Aasen

We propose an empirical measure of the approximate accuracy of feature importance estimates in deep neural networks. Our results across several large-scale image classification datasets show that many popular interpretability methods…

Machine Learning · Computer Science 2019-11-06 Sara Hooker , Dumitru Erhan , Pieter-Jan Kindermans , Been Kim

Data samples collected for training machine learning models are typically assumed to be independent and identically distributed (iid). Recent research has demonstrated that this assumption can be problematic as it simplifies the manifold of…

Machine Learning · Computer Science 2019-10-16 Kaixuan Zhang , Qinglong Wang , Xue Liu , C. Lee Giles

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…

Machine Learning · Computer Science 2023-03-28 Hui Duan , Giray Ökten

Graph sparsification is a key technique for improving inference efficiency in Graph Neural Networks by removing edges with minimal impact on predictions. GNN explainability methods generate local importance scores, which can be aggregated…

Machine Learning · Computer Science 2025-07-29 Selahattin Akkas , Ariful Azad

We present an unsupervised method for aggregating anomalies in tabular datasets by identifying the top-k tabular data quality insights. Each insight consists of a set of anomalous attributes and the corresponding subsets of records that…

Machine Learning · Computer Science 2025-01-14 Manisha Padala , Lokesh Nagalapatti , Atharv Tyagi , Ramasuri Narayanam , Shiv Kumar Saini

We develop a simple and unified framework for nonlinear variable selection that incorporates uncertainty in the prediction function and is compatible with a wide range of machine learning models (e.g., tree ensembles, kernel methods, neural…

Machine Learning · Statistics 2022-05-30 Wenying Deng , Beau Coker , Rajarshi Mukherjee , Jeremiah Zhe Liu , Brent A. Coull

Analyzing spatially varying effects is pivotal in geographic analysis. However, accurately capturing and interpreting this variability is challenging due to the increasing complexity and non-linearity of geospatial data. Recent advancements…

Machine Learning · Computer Science 2024-12-18 Lingbo Liu

Explainable Artificial Intelligence (XAI) techniques, such as SHapley Additive exPlanations (SHAP), have become essential tools for interpreting complex ensemble tree-based models, especially in high-stakes domains such as healthcare…

Artificial Intelligence · Computer Science 2026-02-25 Akshat Dubey , Aleksandar Anžel , Bahar İlgen , Georges Hattab

Due to their power and ease of use, tree-based machine learning models, such as random forests and gradient-boosted tree ensembles, have become very popular. To interpret them, local feature attributions based on marginal expectations, e.g.…

Machine Learning · Computer Science 2024-05-09 Khashayar Filom , Alexey Miroshnikov , Konstandinos Kotsiopoulos , Arjun Ravi Kannan

In the era of "big data", it is becoming more of a challenge to not only build state-of-the-art predictive models, but also gain an understanding of what's really going on in the data. For example, it is often of interest to know which, if…

Machine Learning · Statistics 2018-05-15 Brandon M. Greenwell , Bradley C. Boehmke , Andrew J. McCarthy

Seismic inversion is essential for geophysical exploration and geological assessment, but it is inherently subject to significant uncertainty. This uncertainty stems primarily from the limited information provided by observed seismic data,…

Geophysics · Physics 2024-09-12 Luping Qu , Mauricio Araya-Polo , Laurent Demanet

Interpretable machine learning has emerged as central in leveraging artificial intelligence within high-stakes domains such as healthcare, where understanding the rationale behind model predictions is as critical as achieving high…

Machine Learning · Computer Science 2024-04-30 Christel Sirocchi , Martin Urschler , Bastian Pfeifer

While shallow decision trees may be interpretable, larger ensemble models like gradient-boosted trees, which often set the state of the art in machine learning problems involving tabular data, still remain black box models. As a remedy, the…

Machine Learning · Computer Science 2024-06-21 Maximilian Muschalik , Fabian Fumagalli , Barbara Hammer , Eyke Hüllermeier

This paper proposes a novel approach to explain the predictions made by data-driven methods. Since such predictions rely heavily on the data used for training, explanations that convey information about how the training data affects the…

Machine Learning · Statistics 2022-12-09 Andreas Brandsæter , Ingrid K. Glad

As data emerges as a vital driver of technological and economic advancements, a key challenge is accurately quantifying its value in algorithmic decision-making. The Shapley value, a well-established concept from cooperative game theory,…

Computer Science and Game Theory · Computer Science 2025-11-20 Xi Zheng , Xiangyu Chang , Ruoxi Jia , Yong Tan

Machine learning models are widely applied in various fields. Stakeholders often use post-hoc feature importance methods to better understand the input features' contribution to the models' predictions. The interpretation of the importance…

Machine Learning · Statistics 2024-04-19 Bitya Neuhof , Yuval Benjamini

Shapley values are model-agnostic methods for explaining model predictions. Many commonly used methods of computing Shapley values, known as off-manifold methods, rely on model evaluations on out-of-distribution input samples. Consequently,…

Machine Learning · Statistics 2023-02-28 Muhammad Faaiz Taufiq , Patrick Blöbaum , Lenon Minorics

For neural models to garner widespread public trust and ensure fairness, we must have human-intelligible explanations for their predictions. Recently, an increasing number of works focus on explaining the predictions of neural models in…

Computation and Language · Computer Science 2020-12-15 Oana-Maria Camburu , Eleonora Giunchiglia , Jakob Foerster , Thomas Lukasiewicz , Phil Blunsom