English
Related papers

Related papers: Explainability of Machine Learning Models under Mi…

200 papers

Feature attributions based on the Shapley value are popular for explaining machine learning models; however, their estimation is complex from both a theoretical and computational standpoint. We disentangle this complexity into two factors:…

Machine Learning · Computer Science 2022-07-18 Hugh Chen , Ian C. Covert , Scott M. Lundberg , Su-In Lee

Data Shapley has recently been proposed as a principled framework to quantify the contribution of individual datum in machine learning. It can effectively identify helpful or harmful data points for a learning algorithm. In this paper, we…

Machine Learning · Computer Science 2022-01-20 Yongchan Kwon , James Zou

The complex nature of artificial neural networks raises concerns on their reliability, trustworthiness, and fairness in real-world scenarios. The Shapley value -- a solution concept from game theory -- is one of the most popular explanation…

Machine Learning · Computer Science 2023-12-29 Jacopo Teneggi , Beepul Bharti , Yaniv Romano , Jeremias Sulam

SHAP scores represent the proposed use of the well-known Shapley values in eXplainable Artificial Intelligence (XAI). Recent work has shown that the exact computation of SHAP scores can produce unsatisfactory results. Concretely, for some…

Machine Learning · Computer Science 2024-12-20 Olivier Letoffe , Xuanxiang Huang , Joao Marques-Silva

Nowadays, deep neural networks are widely used in a variety of fields that have a direct impact on society. Although those models typically show outstanding performance, they have been used for a long time as black boxes. To address this,…

Machine Learning · Computer Science 2022-10-11 Huawei Sun , Lorenzo Servadei , Hao Feng , Michael Stephan , Robert Wille , Avik Santra

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…

Artificial Intelligence · Computer Science 2026-05-28 Olivier Létoffé , Xuanxiang Huang , Joao Marques-Silva

This text discusses several popular explanatory methods that go beyond the error measurements and plots traditionally used to assess machine learning models. Some of the explanatory methods are accepted tools of the trade while others are…

Machine Learning · Statistics 2020-06-02 Patrick Hall

Nowadays, the interpretation of why a machine learning (ML) model makes certain inferences is as crucial as the accuracy of such inferences. Some ML models like the decision tree possess inherent interpretability that can be directly…

Machine Learning · Computer Science 2023-04-11 Han Yuan , Mingxuan Liu , Lican Kang , Chenkui Miao , Ying Wu

Analysis of the fairness of machine learning (ML) algorithms recently attracted many researchers' interest. Most ML methods show bias toward protected groups, which limits the applicability of ML models in many applications like crime rate…

Machine Learning · Computer Science 2022-11-03 Haris Mansoor , Sarwan Ali , Shafiq Alam , Muhammad Asad Khan , Umair ul Hassan , Imdadullah Khan

Explaining the predictions of opaque machine learning algorithms is an important and challenging task, especially as complex models are increasingly used to assist in high-stakes decisions such as those arising in healthcare and finance.…

Machine Learning · Computer Science 2022-06-29 David S. Watson

Missing data is a systemic problem in practical scenarios that causes noise and bias when estimating treatment effects. This makes treatment effect estimation from data with missingness a particularly tricky endeavour. A key reason for this…

Machine Learning · Statistics 2023-02-27 Jeroen Berrevoets , Fergus Imrie , Trent Kyono , James Jordon , Mihaela van der Schaar

Machine Learning explainability techniques have been proposed as a means of `explaining' or interrogating a model in order to understand why a particular decision or prediction has been made. Such an ability is especially important at a…

Machine Learning · Statistics 2022-02-28 Matthew J. Vowels

Feature attribution methods such as SHapley Additive exPlanations (SHAP) have become instrumental in understanding machine learning models, but their role in guiding model optimization remains underexplored. In this paper, we propose a…

Machine Learning · Computer Science 2025-08-01 Amal Saadallah

The increasing complexity of foundational models underscores the necessity for explainability, particularly for fine-tuning, the most widely used training method for adapting models to downstream tasks. Instance attribution, one type of…

Machine Learning · Computer Science 2024-06-10 Jingtan Wang , Xiaoqiang Lin , Rui Qiao , Chuan-Sheng Foo , Bryan Kian Hsiang Low

In recent years, the Shapley value and SHAP explanations have emerged as one of the most dominant paradigms for providing post-hoc explanations of black-box models. Despite their well-founded theoretical properties, many recent works have…

Machine Learning · Computer Science 2025-02-21 James Enouen , Yan Liu

Although modern machine learning and deep learning methods allow for complex and in-depth data analytics, the predictive models generated by these methods are often highly complex, and lack transparency. Explainable AI (XAI) methods are…

Machine Learning · Computer Science 2021-06-17 Mythreyi Velmurugan , Chun Ouyang , Catarina Moreira , Renuka Sindhgatta

Recent advances in deep learning have led to interest in training deep learning models on longitudinal healthcare records to predict a range of medical events, with models demonstrating high predictive performance. Predictive performance is…

Machine Learning · Computer Science 2022-11-23 Lin Lee Cheong , Tesfagabir Meharizghi , Wynona Black , Yang Guang , Weilin Meng

Recent work demonstrated the existence of critical flaws in the current use of Shapley values in explainable AI (XAI), i.e. the so-called SHAP scores. These flaws are significant in that the scores provided to a human decision-maker can be…

Artificial Intelligence · Computer Science 2025-02-18 Joao Marques-Silva , Xuanxiang Huang , Olivier Letoffe

In recent years, explainable machine learning methods have been very successful. Despite their success, most explainable machine learning methods are applied to black-box models without any domain knowledge. By incorporating domain…

Machine Learning · Computer Science 2023-09-26 Dangxing Chen

Shapley values have become one of the go-to methods to explain complex models to end-users. They provide a model agnostic post-hoc explanation with foundations in game theory: what is the worth of a player (in machine learning, a feature…

Machine Learning · Computer Science 2023-06-21 Joran Michiels , Maarten De Vos , Johan Suykens