English
Related papers

Related papers: Impossibility Theorems for Feature Attribution

200 papers

Data attribution has become an important component of pricing, auditing, and governance in machine learning pipelines, yet most attribution methods implicitly assume that attribution values faithfully reflect participants' contributions. We…

Machine Learning · Computer Science 2026-05-18 Xian Gao , Bo Hui , Min-Te Sun , Wei-Shinn Ku

We show that utilizing attribution maps for training neural networks can improve regularization of models and thus increase performance. Regularization is key in deep learning, especially when training complex models on relatively small…

Machine Learning · Computer Science 2022-05-31 Christian Tomani , Daniel Cremers

Large Language Models (LLMs) are becoming increasingly popular in pervasive computing due to their versatility and strong performance. However, despite their ubiquitous use, the exact mechanisms underlying their outstanding performance…

Computation and Language · Computer Science 2026-02-02 Alhassan Abdelhalim , Janick Edinger , Sören Laue , Michaela Regneri

Machine learning algorithms often assume that training samples are independent. When data points are connected by a network, the induced dependency between samples is both a challenge, reducing effective sample size, and an opportunity to…

Machine Learning · Statistics 2025-09-22 Tiffany M. Tang , Elizaveta Levina , Ji Zhu

Despite the wide use of explainability techniques to attempt to understand the behavior of Artificial Intelligence (AI), the generated explanations may not always be reliable. An explanation can appear plausible to humans but fail to…

Machine Learning · Computer Science 2026-05-28 Tomás Pereira , João Vitorino , Eva Maia , Isabel Praça

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

The recent criticisms of the robustness of post hoc model approximation explanation methods (like LIME and SHAP) have led to the rise of model-precise abductive explanations. For each data point, abductive explanations provide a minimal…

Artificial Intelligence · Computer Science 2023-10-13 Gagan Biradar , Yacine Izza , Elita Lobo , Vignesh Viswanathan , Yair Zick

The accelerating advancement of generative models has introduced new challenges for detecting AI-generated images, especially in real-world scenarios where novel generation techniques emerge rapidly. Existing learning paradigms are likely…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Qinghui He , Haifeng Zhang , Xiuli Bi , Bo Liu , Chi-Man Pun , Bin Xiao

Graphs (networks) are ubiquitous and allow us to model entities (nodes) and the dependencies (edges) between them. Learning a useful feature representation from graph data lies at the heart and success of many machine learning tasks such as…

We address the critical challenge of applying feature attribution methods to the transformer architecture, which dominates current applications in natural language processing and beyond. Traditional attribution methods to explainable AI…

Machine Learning · Computer Science 2025-01-10 Tobias Leemann , Alina Fastowski , Felix Pfeiffer , Gjergji Kasneci

Learning representations that generalize under distribution shifts is critical for building robust machine learning models. However, despite significant efforts in recent years, algorithmic advances in this direction have been limited. In…

Machine Learning · Computer Science 2025-02-14 Tianren Zhang , Chujie Zhao , Guanyu Chen , Yizhou Jiang , Feng Chen

We show new connections between adversarial learning and explainability for deep neural networks (DNNs). One form of explanation of the output of a neural network model in terms of its input features, is a vector of feature-attributions.…

Machine Learning · Computer Science 2020-07-07 Prasad Chalasani , Jiefeng Chen , Amrita Roy Chowdhury , Somesh Jha , Xi Wu

Evaluating feature attribution methods represents a critical challenge in explainable AI (XAI), as researchers typically rely on perturbation-based metrics when ground truth is unavailable. However, recent work reveals that these evaluation…

Machine Learning · Computer Science 2026-05-12 Gregor Baer , Isel Grau , Chao Zhang , Pieter Van Gorp

In the algorithm selection research, the discussion surrounding algorithm features has been significantly overshadowed by the emphasis on problem features. Although a few empirical studies have yielded evidence regarding the effectiveness…

Machine Learning · Computer Science 2024-06-04 Xingyu Wu , Yan Zhong , Jibin Wu , Yuxiao Huang , Sheng-hao Wu , Kay Chen Tan

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

Classification is a ubiquitous and fundamental problem in artificial intelligence and machine learning, with extensive efforts dedicated to developing more powerful classifiers and larger datasets. However, the classification task is…

Machine Learning · Computer Science 2025-12-22 Mario Franco , Gerardo Febres , Nelson Fernández , Carlos Gershenson

Interpreting the decisions of complex computer vision models is crucial to establish trust and accountability, especially in safety-critical domains. An established approach to interpretability is generating visual attribution maps that…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 David Schinagl , Christian Fruhwirth-Reisinger , Alexander Prutsch , Samuel Schulter , Horst Possegger

Feature attribution methods (FAs) are popular approaches for providing insights into the model reasoning process of making predictions. The more faithful a FA is, the more accurately it reflects which parts of the input are more important…

Computation and Language · Computer Science 2024-01-31 Zhixue Zhao , Nikolaos Aletras

A supervised learning algorithm has access to a distribution of labeled examples, and needs to return a function (hypothesis) that correctly labels the examples. The hypothesis of the learner is taken from some fixed class of functions…

Machine Learning · Computer Science 2020-08-25 Eran Malach , Shai Shalev-Shwartz

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