English
Related papers

Related papers: Prospector Heads: Generalized Feature Attribution …

200 papers

Local and global patterns of an object are closely related. Although each part of an object is incomplete, the underlying attributes about the object are shared among all parts, which makes reasoning the whole object from a single part…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Yongming Rao , Jiwen Lu , Jie Zhou

Using feature attributions for post-hoc explanations is a common practice to understand and verify the predictions of opaque machine learning models. Despite the numerous techniques available, individual methods often produce inconsistent…

Machine Learning · Computer Science 2024-06-10 Thomas Decker , Ananta R. Bhattarai , Jindong Gu , Volker Tresp , Florian Buettner

In this paper, we focus on model generalization and adaptation for cross-domain person re-identification (Re-ID). Unlike existing cross-domain Re-ID methods, leveraging the auxiliary information of those unlabeled target-domain data, we aim…

Computer Vision and Pattern Recognition · Computer Science 2019-05-31 Haijun Liu , Jian Cheng , Shiguang Wang , Wen Wang

Machine learning transparency calls for interpretable explanations of how inputs relate to predictions. Feature attribution is a way to analyze the impact of features on predictions. Feature interactions are the contextual dependence…

Machine Learning · Statistics 2020-06-22 Michael Tsang , Sirisha Rambhatla , Yan Liu

This paper introduces a causal attribution model to enhance the interpretability of large language models (LLMs) and improve their causal reasoning abilities via precise fine-tuning. Despite LLMs' proficiency in diverse tasks, their…

Artificial Intelligence · Computer Science 2026-05-22 Hengrui Cai , Shengjie Liu , Rui Song

This paper introduces Generalized Attention Flow (GAF), a novel feature attribution method for Transformer-based models to address the limitations of current approaches. By extending Attention Flow and replacing attention weights with the…

Machine Learning · Computer Science 2025-02-25 Behrooz Azarkhalili , Maxwell Libbrecht

State-of-the-art attribution methods rely on adversarial sample generation that applies an all-pass filter across the frequency spectrum, discarding fine-grained high-frequency information that is demonstrably important for accurate feature…

Machine Learning · Computer Science 2026-05-11 Ali Yavari , Alireza Mohamadi , Elham Beydaghi , Philipp Seeböck , Rainer A. Leitgeb

An important step towards explaining deep image classifiers lies in the identification of image regions that contribute to individual class scores in the model's output. However, doing this accurately is a difficult task due to the…

Computer Vision and Pattern Recognition · Computer Science 2024-08-01 Steven Stalder , Nathanaël Perraudin , Radhakrishna Achanta , Fernando Perez-Cruz , Michele Volpi

As artificial intelligence becomes increasingly pervasive and powerful, the ability to audit AI-based systems is growing in importance. However, explainability for artificial intelligence systems is not a one-size-fits-all solution;…

Human-Computer Interaction · Computer Science 2025-10-13 Nicola Rossberg , Bennett Kleinberg , Barry O'Sullivan , Luca Longo , Andrea Visentin

Consider the problem of imputing missing values in a dataset. One the one hand, conventional approaches using iterative imputation benefit from the simplicity and customizability of learning conditional distributions directly, but suffer…

Machine Learning · Statistics 2022-06-17 Daniel Jarrett , Bogdan Cebere , Tennison Liu , Alicia Curth , Mihaela van der Schaar

Data attribution methods, which quantify the influence of individual training data points on a machine learning model, have gained increasing popularity in data-centric applications in modern AI. Despite a recent surge of new methods…

Machine Learning · Computer Science 2025-10-24 Weiyi Wang , Junwei Deng , Yuzheng Hu , Shiyuan Zhang , Xirui Jiang , Runting Zhang , Han Zhao , Jiaqi W. Ma

This paper discusses predictive inference and feature selection for generalized linear models with scarce but high-dimensional data. We argue that in many cases one can benefit from a decision theoretically justified two-stage approach:…

Machine Learning · Statistics 2020-11-09 Juho Piironen , Markus Paasiniemi , Aki Vehtari

Recent years have witnessed the widespread use of artificial intelligence (AI) algorithms and machine learning (ML) models. Despite their tremendous success, a number of vital problems like ML model brittleness, their fairness, and the lack…

Artificial Intelligence · Computer Science 2023-08-29 Jinqiang Yu , Alexey Ignatiev , Peter J. Stuckey

As the quality of large language models has improved, there has been increased interest in using them to model non-linguistic tokens. For example, the Decision Transformer recasts agentic decision making as a sequence modeling problem,…

Machine Learning · Computer Science 2025-03-12 Nate Gillman , Daksh Aggarwal , Michael Freeman , Saurabh Singh , Chen Sun

Recently, efficient fine-tuning of large-scale pre-trained models has attracted increasing research interests, where linear probing (LP) as a fundamental module is involved in exploiting the final representations for task-dependent…

Computer Vision and Pattern Recognition · Computer Science 2023-10-03 Mingze Gao , Qilong Wang , Zhenyi Lin , Pengfei Zhu , Qinghua Hu , Jingbo Zhou

We discuss a vulnerability involving a category of attribution methods used to provide explanations for the outputs of convolutional neural networks working as classifiers. It is known that this type of networks are vulnerable to…

Machine Learning · Computer Science 2024-04-10 Miguel Lerma , Mirtha Lucas

This study presents insights gathered from surveys and discussions with specialists in three domains, aiming to find essential elements for a universal explanation framework that could be applied to these and other similar use cases. The…

Machine Learning · Computer Science 2025-04-22 Eduard Barbu , Marharyta Domnich , Raul Vicente , Nikos Sakkas , André Morim

Advances in mechanistic interpretability have identified special attention heads, known as retrieval heads, that are responsible for retrieving information from the context. However, the role of these retrieval heads in improving model…

Computation and Language · Computer Science 2026-04-27 Youmi Ma , Naoaki Okazaki

Leveraging human perception into training of convolutional neural networks (CNN) has boosted generalization capabilities of such models in open-set recognition tasks. One of the active research questions is where (in the model architecture…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Colton R. Crum , Adam Czajka

We present self-speculative masked diffusions, a new class of masked diffusion generative models for discrete data that require significantly fewer function evaluations to generate samples. Standard masked diffusion models predict…

Machine Learning · Statistics 2026-03-09 Andrew Campbell , Valentin De Bortoli , Jiaxin Shi , Arnaud Doucet