English
Related papers

Related papers: On the Robustness of Interpretability Methods

200 papers

Reliability is an essential measure of how closely observed scores represent latent scores (reflecting constructs), assuming some latent variable measurement model. We present a general theoretical framework of reliability, placing emphasis…

Methodology · Statistics 2024-10-29 Yang Liu , Jolynn Pek , Alberto Maydeu-Olivares

As machine learning models are increasingly being employed in various high-stakes settings, it becomes important to ensure that predictions of these models are not only adversarially robust, but also readily explainable to relevant…

Machine Learning · Computer Science 2024-07-25 Satyapriya Krishna , Chirag Agarwal , Himabindu Lakkaraju

Information retrieval models have witnessed a paradigm shift from unsupervised statistical approaches to feature-based supervised approaches to completely data-driven ones that make use of the pre-training of large language models. While…

Information Retrieval · Computer Science 2024-03-05 Saran Pandian , Debasis Ganguly , Sean MacAvaney

Readability is on the cusp of a revolution. Fixed text is becoming fluid as a proliferation of digital reading devices rewrite what a document can do. As past constraints make way for more flexible opportunities, there is great need to…

This paper deals with three tools to compare proof-theoretic strength of formal arithmetical theories: interpretability, $\Pi^0_1$-conservativity and proving restricted consistency. It is well known that under certain conditions these three…

Logic · Mathematics 2016-02-02 Joost J. Joosten

Neural networks achieve outstanding accuracy in classification and regression tasks. However, understanding their behavior still remains an open challenge that requires questions to be addressed on the robustness, explainability and…

Machine Learning · Computer Science 2021-05-13 Anna-Kathrin Kopetzki , Stephan Günnemann

Interpretability provides a toolset for understanding how and why neural networks behave in certain ways. However, there is little unity in the field: most studies employ ad-hoc evaluations and do not share theoretical foundations, making…

We argue that existing definitions of interpretability are not actionable in that they fail to inform users about general, sound, and robust interpretable model design. This makes current interpretability research fundamentally ill-posed.…

Machine Learning · Computer Science 2025-08-04 Pietro Barbiero , Mateo Espinosa Zarlenga , Alberto Termine , Mateja Jamnik , Giuseppe Marra

We introduce a metric for evaluating the robustness of a classifier, with particular attention to adversarial perturbations, in terms of expected functionality with respect to possible adversarial perturbations. A classifier is assumed to…

Machine Learning · Computer Science 2023-09-19 Ryan McCoppin , Colin Dawson , Sean M. Kennedy , Leslie M. Blaha

Explainable recommendation has shown its great advantages for improving recommendation persuasiveness, user satisfaction, system transparency, among others. A fundamental problem of explainable recommendation is how to evaluate the…

Information Retrieval · Computer Science 2022-02-15 Xu Chen , Yongfeng Zhang , Ji-Rong Wen

Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains…

Artificial Intelligence · Computer Science 2018-02-05 Menaka Narayanan , Emily Chen , Jeffrey He , Been Kim , Sam Gershman , Finale Doshi-Velez

The incompressibility method is an elementary yet powerful proof technique. It has been used successfully in many areas. To further demonstrate its power and elegance we exhibit new simple proofs using the incompressibility method.

Computational Complexity · Computer Science 2007-05-23 Tao Jiang , Ming Li , Paul Vitanyi

The huge amount of available data nowadays is a challenge for kernel-based machine learning algorithms like SVMs with respect to runtime and storage capacities. Local approaches might help to relieve these issues and to improve statistical…

Machine Learning · Statistics 2019-03-05 Florian Dumpert

Motivated by the recent discovery that the interpretation maps of CNNs could easily be manipulated by adversarial attacks against network interpretability, we study the problem of interpretation robustness from a new perspective of \Renyi…

Machine Learning · Computer Science 2021-07-06 Ao Liu , Xiaoyu Chen , Sijia Liu , Lirong Xia , Chuang Gan

Recent works have shown explainability and robustness are two crucial ingredients of trustworthy and reliable text classification. However, previous works usually address one of two aspects: i) how to extract accurate rationales for…

Computation and Language · Computer Science 2021-12-21 Dongfang Li , Baotian Hu , Qingcai Chen , Tujie Xu , Jingcong Tao , Yunan Zhang

Along with the successful deployment of deep neural networks in several application domains, the need to unravel the black-box nature of these networks has seen a significant increase recently. Several methods have been introduced to…

Machine Learning · Computer Science 2023-07-06 Adam Ivankay , Mattia Rigotti , Pascal Frossard

In this article I propose an approach for defining replicability for prediction rules. Motivated by a recent NAS report, I start from the perspective that replicability is obtaining consistent results across studies suitable to address the…

Methodology · Statistics 2023-05-03 Giovanni Parmigiani

Explainable Recommendation has been gaining attention over the last few years in industry and academia. Explanations provided along with recommendations in a recommender system framework have many uses: particularly reasoning why a…

Information Retrieval · Computer Science 2024-05-06 Sairamvinay Vijayaraghavan , Prasant Mohapatra

Recent work shows issues of consistency with explanations, with methods generating local explanations that seem reasonable instance-wise, but that are inconsistent across instances. This suggests not only that instance-wise explanations can…

Artificial Intelligence · Computer Science 2022-08-02 Guilherme Paulino-Passos , Francesca Toni

Deep neural networks (DNNs) have had many successes, but they suffer from two major issues: (1) a vulnerability to adversarial examples and (2) a tendency to elude human interpretation. Interestingly, recent empirical and theoretical…

Machine Learning · Computer Science 2020-12-07 Adam Noack , Isaac Ahern , Dejing Dou , Boyang Li