English
Related papers

Related papers: "Is your explanation stable?": A Robustness Evalua…

200 papers

Explainable AI (XAI) is critical for building trust in complex machine learning models, yet mainstream attribution methods often provide an incomplete, static picture of a model's final state. By collapsing a feature's role into a single…

Machine Learning · Computer Science 2025-11-03 Hamed Najafi , Dongsheng Luo , Jason Liu

Reliable pattern recognition systems should exhibit consistent behavior across similar inputs, and their explanations should remain stable. However, most Explainable AI evaluations remain instance centric and do not explicitly quantify…

Artificial Intelligence · Computer Science 2026-04-07 Abu Noman Md Sakib , Zhensen Wang , Merjulah Roby , Zijie Zhang

Improving model robustness against potential modality noise, as an essential step for adapting multimodal models to real-world applications, has received increasing attention among researchers. For Multimodal Sentiment Analysis (MSA), there…

Multimedia · Computer Science 2022-11-28 Huisheng Mao , Baozheng Zhang , Hua Xu , Ziqi Yuan , Yihe Liu

This paper studies the robustness of feature attribution methods for deep neural networks. It challenges the current notion of attributional robustness that largely ignores the difference in the model's outputs and introduces a new way of…

Machine Learning · Computer Science 2025-12-09 Panagiota Kiourti , Anu Singh , Preeti Duraipandian , Weichao Zhou , Wenchao Li

Feature attribution methods attempt to explain neural network predictions by identifying relevant features. However, establishing a cohesive framework for assessing feature attribution remains a challenge. There are several views through…

Machine Learning · Computer Science 2024-11-26 Yawei Li , Yang Zhang , Kenji Kawaguchi , Ashkan Khakzar , Bernd Bischl , Mina Rezaei

Feature attributions are a popular tool for explaining the behavior of Deep Neural Networks (DNNs), but have recently been shown to be vulnerable to attacks that produce divergent explanations for nearby inputs. This lack of robustness is…

Machine Learning · Computer Science 2020-10-23 Zifan Wang , Haofan Wang , Shakul Ramkumar , Matt Fredrikson , Piotr Mardziel , Anupam Datta

It is a mystery which input features contribute to a neural network's output. Various explanation (feature attribution) methods are proposed in the literature to shed light on the problem. One peculiar observation is that these explanations…

Machine Learning · Computer Science 2022-03-07 Ashkan Khakzar , Pedram Khorsandi , Rozhin Nobahari , Nassir Navab

While recent years have witnessed the emergence of various explainable methods in machine learning, to what degree the explanations really represent the reasoning process behind the model prediction -- namely, the faithfulness of…

Computation and Language · Computer Science 2021-09-07 Yingqiang Ge , Shuchang Liu , Zelong Li , Shuyuan Xu , Shijie Geng , Yunqi Li , Juntao Tan , Fei Sun , Yongfeng Zhang

Controlling the patterns a model learns is essential to preventing reliance on irrelevant or misleading features. Such reliance on irrelevant features, often called shortcut features, has been observed across domains, including medical…

Machine Learning · Computer Science 2025-09-23 Mihnea Ghitu , Vihari Piratla , Matthew Wicker

Feature attribution is a fundamental task in both machine learning and data analysis, which involves determining the contribution of individual features or variables to a model's output. This process helps identify the most important…

Machine Learning · Computer Science 2023-10-26 Jinfeng Zhong , Elsa Negre

Test-time adaptation (TTA) aims to address distributional shifts between training and testing data using only unlabeled test data streams for continual model adaptation. However, most TTA methods assume benign test streams, while test…

Machine Learning · Computer Science 2023-10-17 Taesik Gong , Yewon Kim , Taeckyung Lee , Sorn Chottananurak , Sung-Ju Lee

As artificial intelligence plays an increasingly important role in our society, there are ethical and moral obligations for both businesses and researchers to ensure that their machine learning models are designed, deployed, and maintained…

Machine Learning · Computer Science 2020-07-07 Shubham Sharma , Jette Henderson , Joydeep Ghosh

Human agents routinely reason on instances with incomplete and muddied data (and weigh the cost of obtaining further features). In contrast, much of ML is devoted to the unrealistic, sterile environment where all features are observed and…

Machine Learning · Computer Science 2024-10-08 Yang Li , Junier Oliva

When machine learning supports decision-making in safety-critical systems, it is important to verify and understand the reasons why a particular output is produced. Although feature importance calculation approaches assist in…

Machine Learning · Statistics 2020-09-14 Divish Rengasamy , Benjamin Rothwell , Grazziela Figueredo

We present a novel method for reliably explaining the predictions of neural networks. We consider an explanation reliable if it identifies input features relevant to the model output by considering the input and the neighboring data points.…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Dohun Lim , Hyeonseok Lee , Sungchan Kim

To better understand the output of deep neural networks (DNN), attribution based methods have been an important approach for model interpretability, which assign a score for each input dimension to indicate its importance towards the model…

Computer Vision and Pattern Recognition · Computer Science 2023-12-22 Zhiyu Zhu , Huaming Chen , Jiayu Zhang , Xinyi Wang , Zhibo Jin , Minhui Xue , Dongxiao Zhu , Kim-Kwang Raymond Choo

Deep neural network predictions are notoriously difficult to interpret. Feature attribution methods aim to explain these predictions by identifying the contribution of each input feature. Faithfulness, often evaluated using the area over…

Machine Learning · Computer Science 2025-05-26 Joakim Edin , Andreas Geert Motzfeldt , Casper L. Christensen , Tuukka Ruotsalo , Lars Maaløe , Maria Maistro

Mechanistic Interpretability (MI) aims to reverse-engineer model behaviors by identifying functional sub-networks. Yet, the scientific validity of these findings depends on their stability. In this work, we argue that circuit discovery is…

Machine Learning · Computer Science 2026-02-04 Maxime Méloux , François Portet , Maxime Peyrard

Assured AI in unrestricted settings is a critical problem. Our framework addresses AI assurance challenges lying at the intersection of domain adaptation, fairness, and counterfactuals analysis, operating via the discovery and intervention…

Machine Learning · Computer Science 2021-11-19 William Paul , Philippe Burlina

Motivation: Protein function prediction is a challenging task and an open problem in computational biology. The Critical Assessment of protein Function Annotation (CAFA) is a triennial, community-driven initiative that provides an…

Quantitative Methods · Quantitative Biology 2026-04-23 An Phan , Yanli Wang , Frimpong Boadu , Maxat Kulmanov , Robert Hoehndorf , Jianlin Cheng , Predrag Radivojac , Iddo Friedberg