English
Related papers

Related papers: Explanation Regularisation through the Lens of Att…

200 papers

Neural networks are powerful function approximators with tremendous potential in learning complex distributions. However, they are prone to overfitting on spurious patterns. Bayesian inference provides a principled way to regularize neural…

Machine Learning · Computer Science 2024-12-02 Yanzhe Bekkemoen , Helge Langseth

Recent years have seen the introduction of a range of methods for post-hoc explainability of image classifier predictions. However, these post-hoc explanations may not always be faithful to classifier predictions, which poses a significant…

Machine Learning · Computer Science 2021-09-28 Ruiwen Li , Zhibo Zhang , Jiani Li , Chiheb Trabelsi , Scott Sanner , Jongseong Jang , Yeonjeong Jeong , Dongsub Shim

Recent explainability related studies have shown that state-of-the-art DNNs do not always adopt correct evidences to make decisions. It not only hampers their generalization but also makes them less likely to be trusted by end-users. In…

Machine Learning · Computer Science 2019-08-16 Mengnan Du , Ninghao Liu , Fan Yang , Xia Hu

Sparse autoencoders (SAEs) are widely used in mechanistic interpretability to project LLM activations onto sparse latent spaces. However, sparsity alone is an imperfect proxy for interpretability, and current training objectives often…

Machine Learning · Computer Science 2026-04-09 Vivek Narayanaswamy , Kowshik Thopalli , Bhavya Kailkhura , Wesam Sakla

We examine whether data generated by explanation techniques, which promote a process of self-reflection, can improve classifier performance. Our work is based on the idea that humans have the ability to make quick, intuitive decisions as…

Machine Learning · Computer Science 2025-03-05 Johannes Schneider , Michalis Vlachos

In many settings, it is important that a model be capable of providing reasons for its predictions (i.e., the model must be interpretable). However, the model's reasoning may not conform with well-established knowledge. In such cases, while…

Machine Learning · Computer Science 2019-02-19 Jiaxuan Wang , Jeeheh Oh , Haozhu Wang , Jenna Wiens

Interpretability provides a means for humans to verify aspects of machine learning (ML) models and empower human+ML teaming in situations where the task cannot be fully automated. Different contexts require explanations with different…

Machine Learning · Computer Science 2024-07-15 Zixi Chen , Varshini Subhash , Marton Havasi , Weiwei Pan , Finale Doshi-Velez

We explore the question of whether the representations learned by classifiers can be used to enhance the quality of generative models. Our conjecture is that labels correspond to characteristics of natural data which are most salient to…

Machine Learning · Statistics 2016-02-16 Alex Lamb , Vincent Dumoulin , Aaron Courville

In application domains such as healthcare, we want accurate predictive models that are also causally interpretable. In pursuit of such models, we propose a causal regularizer to steer predictive models towards causally-interpretable…

Machine Learning · Computer Science 2017-02-24 Mohammad Taha Bahadori , Krzysztof Chalupka , Edward Choi , Robert Chen , Walter F. Stewart , Jimeng Sun

Existing training criteria in automatic speech recognition(ASR) permit the model to freely explore more than one time alignments between the feature and label sequences. In this paper, we use entropy to measure a model's uncertainty, i.e.…

Computation and Language · Computer Science 2022-12-26 Ehsan Variani , Ke Wu , David Rybach , Cyril Allauzen , Michael Riley

We present Expected Statistic Regularization (ESR), a novel regularization technique that utilizes low-order multi-task structural statistics to shape model distributions for semi-supervised learning on low-resource datasets. We study ESR…

Computation and Language · Computer Science 2022-10-19 Thomas Effland , Michael Collins

This paper introduces an explanation framework designed to enhance the quality of rules in knowledge-based reasoning systems based on dataset-driven insights. The traditional method for rule induction from data typically requires…

Artificial Intelligence · Computer Science 2025-02-04 Oshani Seneviratne , Brendan Capuzzo , William Van Woensel

Data augmentation is used in machine learning to make the classifier invariant to label-preserving transformations. Usually this invariance is only encouraged implicitly by including a single augmented input during training. However,…

Machine Learning · Computer Science 2022-03-08 Aleksander Botev , Matthias Bauer , Soham De

Machine learning is a powerful tool for predicting human-related outcomes, from credit scores to heart attack risks. But when deployed, learned models also affect how users act in order to improve outcomes, whether predicted or real. The…

Machine Learning · Computer Science 2020-06-24 Nir Rosenfeld , Sophie Hilgard , Sai Srivatsa Ravindranath , David C. Parkes

Although deep models achieve high predictive performance, it is difficult for humans to understand the predictions they made. Explainability is important for real-world applications to justify their reliability. Many example-based…

Machine Learning · Statistics 2021-12-08 Tomoharu Iwata , Yuya Yoshikawa

Explanations shed light on a machine learning model's rationales and can aid in identifying deficiencies in its reasoning process. Explanation generation models are typically trained in a supervised way given human explanations. When such…

Machine Learning · Computer Science 2021-09-09 Pepa Atanasova , Jakob Grue Simonsen , Christina Lioma , Isabelle Augenstein

This paper investigates the use of regularization priors in the context of treatment effect estimation using observational data where the number of control variables is large relative to the number of observations. First, the phenomenon of…

Methodology · Statistics 2016-12-30 P. Richard Hahn , Carlos M. Carvalho , Jingyu He , David Puelz

Machine learning algorithms typically require abundant data under a stationary environment. However, environments are nonstationary in many real-world applications. Critical issues lie in how to effectively adapt models under an…

Machine Learning · Statistics 2020-06-29 Masaaki Takada , Hironori Fujisawa

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

Model explainability is crucial for human users to be able to interpret how a proposed classifier assigns labels to data based on its feature values. We study generalized linear models constructed using sets of feature value rules, which…

Machine Learning · Statistics 2023-11-06 Sanjeeb Dash , Soumyadip Ghosh , Joao Goncalves , Mark S. Squillante