English
Related papers

Related papers: Baseline Computation for Attribution Methods Based…

200 papers

Deep neural networks achieve superior performance for learning from independent and identically distributed (i.i.d.) data. However, their performance deteriorates significantly when handling out-of-distribution (OoD) data, where the…

Machine Learning · Computer Science 2023-07-25 Haoyue Bai , Ceyuan Yang , Yinghao Xu , S. -H. Gary Chan , Bolei Zhou

Interpretability methods for neural networks are difficult to evaluate because we do not understand the black-box models typically used to test them. This paper proposes a framework in which interpretability methods are evaluated using…

Machine Learning · Computer Science 2020-10-20 Yiding Hao

Neural networks are increasingly finding their way into the realm of graphs and modeling relationships between features. Concurrently graph neural network explanation approaches are being invented to uncover relationships between the nodes…

Machine Learning · Computer Science 2024-01-02 Razieh Rezaei , Alireza Dizaji , Ashkan Khakzar , Anees Kazi , Nassir Navab , Daniel Rueckert

Neural networks require a careful design in order to perform properly on a given task. In particular, selecting a good activation function (possibly in a data-dependent fashion) is a crucial step, which remains an open problem in the…

Machine Learning · Statistics 2020-06-24 Simone Scardapane , Michele Scarpiniti , Danilo Comminiello , Aurelio Uncini

The main XAI attribution methods for deep neural networks -- GradCAM, SHAP, LIME, Integrated Gradients -- operate on separate theoretical foundations and are not formally comparable. We present GRALIS (Gradient-Riesz Averaged…

Machine Learning · Computer Science 2026-05-20 Raimondo Fanale

Large-scale diffusion models have made significant advances in image generation, particularly through cross-attention mechanisms. While cross-attention has been well-studied in text-to-image tasks, their interpretability in image-to-image…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Junseo Park , Hyeryung Jang

Integrated Gradients (IG), a widely used axiomatic path-based attribution method, assigns importance scores to input features by integrating model gradients along a straight path from a baseline to the input. While effective in some cases,…

Machine Learning · Computer Science 2026-02-27 Sina Salek , Joseph Enguehard

Recently, applying deep neural networks in IR has become an important and timely topic. For instance, Neural Ranking Models(NRMs) have shown promising performance compared to the traditional ranking models. However, explaining the ranking…

Information Retrieval · Computer Science 2020-05-13 Jaekeol Choi , Jungin Choi , Wonjong Rhee

We propose a parametric integral probability metric (IPM) to measure the discrepancy between two probability measures. The proposed IPM leverages a specific parametric family of discriminators, such as single-node neural networks with ReLU…

Machine Learning · Statistics 2025-04-29 Yuha Park , Kunwoong Kim , Insung Kong , Yongdai Kim

Identifying the root causes of outliers is a fundamental problem in causal inference and anomaly detection. Traditional approaches based on heuristics or counterfactual reasoning often struggle under uncertainty and high-dimensional…

Machine Learning · Computer Science 2026-02-02 Phuoc Nguyen , Truyen Tran , Sunil Gupta , Svetha Venkatesh

We present a general convergent class of reinforcement learning algorithms that is founded on two distinct principles: (1) mapping value estimates to a different space using arbitrary functions from a broad class, and (2) linearly…

Machine Learning · Computer Science 2022-03-18 Mehdi Fatemi , Arash Tavakoli

Feature attribution methods are popular in interpretable machine learning. These methods compute the attribution of each input feature to represent its importance, but there is no consensus on the definition of "attribution", leading to…

Machine Learning · Computer Science 2021-12-16 Yilun Zhou , Serena Booth , Marco Tulio Ribeiro , Julie Shah

Interpreting the decision-making process of deep convolutional neural networks remains a central challenge in achieving trustworthy and transparent artificial intelligence. Explainable AI (XAI) techniques, particularly Class Activation Map…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Hajar Dekdegue , Moncef Garouani , Josiane Mothe , Jordan Bernigaud

A two-terminal interactive distributed source coding problem with alternating messages for function computation at both locations is studied. For any number of messages, a computable characterization of the rate region is provided in terms…

Information Theory · Computer Science 2008-11-13 Nan Ma , Prakash Ishwar

We propose a simple interpolation-based method for the efficient approximation of gradients in neural ODE models. We compare it with the reverse dynamic method (known in the literature as "adjoint method") to train neural ODEs on…

Neural and Evolutionary Computing · Computer Science 2020-11-03 Talgat Daulbaev , Alexandr Katrutsa , Larisa Markeeva , Julia Gusak , Andrzej Cichocki , Ivan Oseledets

In this paper, we introduce the neural empirical interpolation method (NEIM), a neural network-based alternative to the discrete empirical interpolation method for reducing the time complexity of computing the nonlinear term in a reduced…

Numerical Analysis · Mathematics 2025-05-13 Max Hirsch , Federico Pichi , Jan S. Hesthaven

Prior gradient-based attribution-map methods rely on handcrafted propagation rules for the non-linear/activation layers during the backward pass, so as to produce gradients of the input and then the attribution map. Despite the promising…

Computer Vision and Pattern Recognition · Computer Science 2020-10-15 Yiding Yang , Jiayan Qiu , Mingli Song , Dacheng Tao , Xinchao Wang

Various attribution methods have been developed to explain deep neural networks (DNNs) by inferring the attribution/importance/contribution score of each input variable to the final output. However, existing attribution methods are often…

Machine Learning · Computer Science 2023-03-07 Huiqi Deng , Na Zou , Mengnan Du , Weifu Chen , Guocan Feng , Ziwei Yang , Zheyang Li , Quanshi Zhang

We conducted a reproducibility study on Integrated Gradients (IG) based methods and the Important Direction Gradient Integration (IDGI) framework. IDGI eliminates the explanation noise in each step of the computation of IG-based methods…

Numerical Analysis · Mathematics 2024-09-17 Shree Singhi , Anupriya Kumari

As a prominent attribution-based explanation algorithm, Integrated Gradients (IG) is widely adopted due to its desirable explanation axioms and the ease of gradient computation. It measures feature importance by averaging the model's output…

Computation and Language · Computer Science 2021-09-01 Soumya Sanyal , Xiang Ren