English
Related papers

Related papers: Utilizing Mutations to Evaluate Interpretability o…

200 papers

Deep neural networks are often considered opaque systems, prompting the need for explainability methods to improve trust and accountability. Existing approaches typically attribute test-time predictions either to input features (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Aziz Bacha , Thomas George

Neural pathways as model explanations consist of a sparse set of neurons that provide the same level of prediction performance as the whole model. Existing methods primarily focus on accuracy and sparsity but the generated pathways may…

Computer Vision and Pattern Recognition · Computer Science 2023-09-19 Xinmiao Lin , Wentao Bao , Qi Yu , Yu Kong

We implement a visual interpretability method Layer-wise Relevance Propagation (LRP) on top of 3D U-Net trained to perform lesion segmentation on the small dataset of multi-modal images provided by ISLES 2017 competition. We demonstrate…

Image and Video Processing · Electrical Eng. & Systems 2020-01-14 Erico Tjoa , Guo Heng , Lu Yuhao , Cuntai Guan

This paper studies the robustness of feature attribution methods for deep neural networks. It challenges the current notion of attributional robustness that largely ignores the difference in the model's outputs and introduces a new way of…

Machine Learning · Computer Science 2025-12-09 Panagiota Kiourti , Anu Singh , Preeti Duraipandian , Weichao Zhou , Wenchao Li

Gradient-based attribution methods can aid in the understanding of convolutional neural networks (CNNs). However, the redundancy of attribution features and the gradient saturation problem, which weaken the ability to identify significant…

Computer Vision and Pattern Recognition · Computer Science 2021-04-13 An Zhang , Xiang Wang , Chengfang Fang , Jie Shi , Tat-seng Chua , Zehua Chen

Uncertainty estimation for machine learning models is of high importance in many scenarios such as constructing the confidence intervals for model predictions and detection of out-of-distribution or adversarially generated points. In this…

Machine Learning · Computer Science 2022-05-06 Kirill Fedyanin , Evgenii Tsymbalov , Maxim Panov

Deep learning models are widely applied in the signal processing community, yet their inner working procedure is often treated as a black box. In this paper, we investigate the use of eXplainable Artificial Intelligence (XAI) techniques to…

Audio and Speech Processing · Electrical Eng. & Systems 2024-04-29 Luca Comanducci , Fabio Antonacci , Augusto Sarti

Graph convolutional networks (GCNs) have achieved great success in graph representation learning by extracting high-level features from nodes and their topology. Since GCNs generally follow a message-passing mechanism, each node aggregates…

Machine Learning · Computer Science 2023-09-07 Wei Duan , Junyu Xuan , Maoying Qiao , Jie Lu

Convolutional Neural Networks (CNNs) have proven to be highly effective in solving a broad spectrum of computer vision tasks, such as classification, identification, and segmentation. These methods can be deployed in both centralized and…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-12 Victor Forattini Jansen , Emanuel Teixeira Martins , Yasmin Souza Lima , Flavio de Oliveira Silva , Rodrigo Moreira , Larissa Ferreira Rodrigues Moreira

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

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

We analyze numerical properties of Layer-wise relevance propagation (LRP)-type attribution methods by representing them as a product of modified gradient matrices. This representation creates an analogy to matrix multiplications of…

Machine Learning · Computer Science 2025-09-12 Alexander Binder , Nastaran Takmil-Homayouni , Urun Dogan

Neural networks and evolutionary computation have a rich intertwined history. They most commonly appear together when an evolutionary algorithm optimises the parameters and topology of a neural network for reinforcement learning problems,…

Neural and Evolutionary Computing · Computer Science 2016-04-15 Alexander W. Churchill , Siddharth Sigtia , Chrisantha Fernando

Deep neural networks have excelled on a wide range of problems, from vision to language and game playing. Neural networks very gradually incorporate information into weights as they process data, requiring very low learning rates. If the…

Deep Neural Networks (DNNs) require very large amounts of computation both for training and for inference when deployed in the field. Many different algorithms have been proposed to implement the most computationally expensive layers of…

Performance · Computer Science 2018-11-05 Andrew Anderson , David Gregg

In the field of autonomous driving and robotics, point clouds are showing their excellent real-time performance as raw data from most of the mainstream 3D sensors. Therefore, point cloud neural networks have become a popular research…

Computer Vision and Pattern Recognition · Computer Science 2021-08-19 Hanxiao Tan , Helena Kotthaus

Graph Neural Networks (GNNs) are deep learning models that take graph data as inputs, and they are applied to various tasks such as traffic prediction and molecular property prediction. However, owing to the complexity of the GNNs, it has…

Machine Learning · Computer Science 2021-11-02 Tetsu Kasanishi , Xueting Wang , Toshihiko Yamasaki

Deep neural networks (DNNs) have been shown lack of robustness for the vulnerability of their classification to small perturbations on the inputs. This has led to safety concerns of applying DNNs to safety-critical domains. Several…

Machine Learning · Computer Science 2021-02-24 Jianlin Li , Pengfei Yang , Jiangchao Liu , Liqian Chen , Xiaowei Huang , Lijun Zhang

Reasoning with knowledge expressed in natural language and Knowledge Bases (KBs) is a major challenge for Artificial Intelligence, with applications in machine reading, dialogue, and question answering. General neural architectures that…

Machine Learning · Computer Science 2019-12-24 Pasquale Minervini , Matko Bošnjak , Tim Rocktäschel , Sebastian Riedel , Edward Grefenstette

While attribution methods, such as Shapley values, are widely used to explain the importance of features or training data in traditional machine learning, their application to Large Language Models (LLMs), particularly within…

Machine Learning · Computer Science 2025-07-08 Ikhtiyor Nematov , Tarik Kalai , Elizaveta Kuzmenko , Gabriele Fugagnoli , Dimitris Sacharidis , Katja Hose , Tomer Sagi