English
Related papers

Related papers: MINAR: Mechanistic Interpretability for Neural Alg…

200 papers

Graph Neural Networks (GNNs) are a powerful representational tool for solving problems on graph-structured inputs. In almost all cases so far, however, they have been applied to directly recovering a final solution from raw inputs, without…

Machine Learning · Statistics 2020-01-16 Petar Veličković , Rex Ying , Matilde Padovano , Raia Hadsell , Charles Blundell

Graph neural networks (GNNs) are powerful tools on graph data. However, their predictions are mis-calibrated and lack interpretability, limiting their adoption in critical applications. To address this issue, we propose a new…

Machine Learning · Computer Science 2025-08-26 Lingkai Kong , Haotian Sun , Yuchen Zhuang , Haorui Wang , Wenhao Mu , Chao Zhang

Computationally explicit hypotheses of brain function derived from machine learning (ML)-based models have recently revolutionized neuroscience. Despite the unprecedented ability of these artificial neural networks (ANNs) to capture…

Neurons and Cognition · Quantitative Biology 2023-12-12 Kohitij Kar , Simon Kornblith , Evelina Fedorenko

Machine learning-based methods have achieved successful applications in machinery fault diagnosis. However, the main limitation that exists for these methods is that they operate as a black box and are generally not interpretable. This…

Machine Learning · Computer Science 2022-04-20 Gang Chen , Yu Lu , Rong Su , Zhaodan Kong

Intrinsic interpretability of graph neural networks (GNNs) is to find a small subset of the input graph's features -- rationale -- which guides the model prediction. Unfortunately, the leading rationalization models often rely on data…

Machine Learning · Computer Science 2022-02-01 Ying-Xin Wu , Xiang Wang , An Zhang , Xiangnan He , Tat-Seng Chua

Interpretability of deep neural networks (DNNs) is essential since it enables users to understand the overall strengths and weaknesses of the models, conveys an understanding of how the models will behave in the future, and how to diagnose…

Computer Vision and Pattern Recognition · Computer Science 2017-03-31 Yinpeng Dong , Hang Su , Jun Zhu , Bo Zhang

Graph Neural Networks (GNNs) have emerged as the predominant approach for learning over graph-structured data. However, most GNNs operate as black-box models and require post-hoc explanations, which may not suffice in high-stakes scenarios…

Machine Learning · Computer Science 2025-10-14 Maya Bechler-Speicher , Amir Globerson , Ran Gilad-Bachrach

Large Language Models (LLMs) have experienced a rapid rise in AI, changing a wide range of applications with their advanced capabilities. As these models become increasingly integral to decision-making, the need for thorough…

Machine Learning · Computer Science 2024-01-09 Jatin Nainani

Recent work on neural algorithmic reasoning has demonstrated that graph neural networks (GNNs) could learn to execute classical algorithms. Doing so, however, has always used a recurrent architecture, where each iteration of the GNN aligns…

Machine Learning · Computer Science 2024-04-10 Dobrik Georgiev , Pietro Liò , Davide Buffelli

Neural Algorithmic Reasoning is an emerging area of machine learning which seeks to infuse algorithmic computation in neural networks, typically by training neural models to approximate steps of classical algorithms. In this context, much…

Machine Learning · Computer Science 2023-02-10 Danilo Numeroso , Davide Bacciu , Petar Veličković

Graph Neural Networks (GNNs) have achieved state-of-the-art performance in solving graph classification tasks. However, most GNN architectures aggregate information from all nodes and edges in a graph, regardless of their relevance to the…

Machine Learning · Statistics 2024-04-19 Pablo Sanchez-Martin , Kinaan Aamir Khan , Isabel Valera

Mechanistic Interpretability aims to understand neural networks through causal explanations. We argue for the Explanatory View Hypothesis: that Mechanistic Interpretability research is a principled approach to understanding models because…

Machine Learning · Computer Science 2025-05-05 Kola Ayonrinde , Louis Jaburi

Graph Neural Networks (GNNs) have become a standard approach for learning from graph-structured data. However, their reliance on parametric classifiers (most often linear softmax layers) limits interpretability and sometimes hinders…

Machine Learning · Computer Science 2026-02-03 Zeljko Bolevic , Milos Brajovic , Isidora Stankovic , Ljubisa Stankovic

Graph Neural Networks (GNNs) are a powerful tool for machine learning on graphs.GNNs combine node feature information with the graph structure by recursively passing neural messages along edges of the input graph. However, incorporating…

Machine Learning · Computer Science 2019-11-15 Rex Ying , Dylan Bourgeois , Jiaxuan You , Marinka Zitnik , Jure Leskovec

Abstract reasoning and logic inference are difficult problems for neural networks, yet essential to their applicability in highly structured domains. In this work we demonstrate that a well known technique such as spectral regularization…

Artificial Intelligence · Computer Science 2020-11-20 Victor Kolev , Bogdan Georgiev , Svetlin Penkov

Neural networks have succeeded in many reasoning tasks. Empirically, these tasks require specialized network structures, e.g., Graph Neural Networks (GNNs) perform well on many such tasks, but less structured networks fail. Theoretically,…

Machine Learning · Computer Science 2020-02-18 Keyulu Xu , Jingling Li , Mozhi Zhang , Simon S. Du , Ken-ichi Kawarabayashi , Stefanie Jegelka

*Automated circuit discovery* is a central tool in mechanistic interpretability for identifying the internal components of neural networks responsible for specific behaviors. While prior methods have made significant progress, they…

Machine Learning · Computer Science 2026-02-20 Itamar Hadad , Guy Katz , Shahaf Bassan

Interpretable insights from predictive models remain critical in bio-statistics, particularly when assessing causality, where classical statistical and machine learning methods often provide inherent clarity. While Neural Networks (NNs)…

Applications · Statistics 2025-05-02 Jean-Baptiste A. Conan

The black box nature of deep neural networks poses a significant challenge for the deployment of transparent and trustworthy artificial intelligence (AI) systems. With the growing presence of AI in society, it becomes increasingly important…

Machine Learning · Computer Science 2025-11-25 Bianka Kowalska , Halina Kwaśnicka

In this paper, we investigate the degree of explainability of graph neural networks (GNNs). Existing explainers work by finding global/local subgraphs to explain a prediction, but they are applied after a GNN has already been trained. Here,…

Machine Learning · Computer Science 2022-12-21 Indro Spinelli , Simone Scardapane , Aurelio Uncini