Cover Image

From Weight Perturbation to Feature Attribution for Explaining Fully Connected Neural Networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lymperopoulos, Thodoris, Kanellopoulou, Denia
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Explaining Concept Shift with Interpretable Feature Attribution
by: Lyu, Ruiqi, et al.
Published: (2025)

GOAt: Explaining Graph Neural Networks via Graph Output Attribution
by: Lu, Shengyao, et al.
Published: (2024)

On Discprecncies between Perturbation Evaluations of Graph Neural Network Attributions
by: Rezaei, Razieh, et al.
Published: (2024)

Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools
by: Lymperopoulos, Panagiotis, et al.
Published: (2025)

Graph Pruning for Enumeration of Minimal Unsatisfiable Subsets
by: Lymperopoulos, Panagiotis, et al.
Published: (2024)

Distribution-Based Feature Attribution for Explaining the Predictions of Any Classifier
by: Li, Xinpeng, et al.
Published: (2025)

Toward Understanding the Disagreement Problem in Neural Network Feature Attribution
by: Koenen, Niklas, et al.
Published: (2024)

Matrix Completion via Nonsmooth Regularization of Fully Connected Neural Networks
by: Faramarzi, Sajad, et al.
Published: (2024)

New Approximation Results and Optimal Estimation for Fully Connected Deep Neural Networks
by: Tang, Zhaoji
Published: (2025)

Explaining Neural Networks with Reasons
by: Hornischer, Levin, et al.
Published: (2025)

GRAFT: Auditing Graph Neural Networks via Global Feature Attribution
by: Sahoo, Rishi Raj, et al.
Published: (2026)

Depth Degeneracy in Neural Networks: Vanishing Angles in Fully Connected ReLU Networks on Initialization
by: Jakub, Cameron, et al.
Published: (2023)

Enhancing Visual Feature Attribution via Weighted Integrated Gradients
by: Tuan, Kien Tran Duc, et al.
Published: (2025)

Explaining Hypergraph Neural Networks: From Local Explanations to Global Concepts
by: Su, Shiye, et al.
Published: (2024)

On How Iterative Magnitude Pruning Discovers Local Receptive Fields in Fully Connected Neural Networks
by: Redman, William T., et al.
Published: (2024)

One Wave To Explain Them All: A Unifying Perspective On Feature Attribution
by: Kasmi, Gabriel, et al.
Published: (2024)

From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context
by: Baghershahi, Peyman, et al.
Published: (2025)

Synthesizing real-world distributions from high-dimensional Gaussian Noise with Fully Connected Neural Network
by: Komorniczak, Joanna
Published: (2026)

Refining Filter Global Feature Weighting for Fully-Unsupervised Clustering
by: Galis, Fabian, et al.
Published: (2025)

Mitigating Overfitting in Graph Neural Networks via Feature and Hyperplane Perturbation
by: Choi, Yoonhyuk, et al.
Published: (2022)

Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete
by: Bertschinger, Daniel, et al.
Published: (2022)

Perturbation on Feature Coalition: Towards Interpretable Deep Neural Networks
by: Hu, Xuran, et al.
Published: (2024)

Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation
by: Chen, Xuexin, et al.
Published: (2024)

A Closed-form Solution for Weight Optimization in Fully-connected Feed-forward Neural Networks
by: Tomic, Slavisa, et al.
Published: (2024)

Relevant Walk Search for Explaining Graph Neural Networks
by: Xiong, Ping, et al.
Published: (2026)

Explaining Deep Neural Networks by Leveraging Intrinsic Methods
by: La Rosa, Biagio
Published: (2024)

Self-Explaining Neural Networks for Business Process Monitoring
by: Bassan, Shahaf, et al.
Published: (2025)

COMBINEX: A Unified Counterfactual Explainer for Graph Neural Networks via Node Feature and Structural Perturbations
by: Giorgi, Flavio, et al.
Published: (2025)

From SGD to Spectra: A Theory of Neural Network Weight Dynamics
by: Olsen, Brian Richard, et al.
Published: (2025)

Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups
by: You, Weiqiu, et al.
Published: (2023)

Graph-based Integrated Gradients for Explaining Graph Neural Networks
by: Simpson, Lachlan, et al.
Published: (2025)

Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks
by: Chen, Zhuomin, et al.
Published: (2024)

Fully Automatic Neural Network Reduction for Formal Verification
by: Ladner, Tobias, et al.
Published: (2023)

Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasons
by: Bassan, Shahaf, et al.
Published: (2025)

Explaining Risks: Axiomatic Risk Attributions for Financial Models
by: Chen, Dangxing
Published: (2025)

Explaining Bayesian Neural Networks
by: Bykov, Kirill, et al.
Published: (2021)

The Attribution Contract: Feature Attribution for Generative Language Models
by: Nguyen, Giang
Published: (2026)

LogicXGNN: Grounded Logical Rules for Explaining Graph Neural Networks
by: Geng, Chuqin, et al.
Published: (2025)

BetaExplainer: A Probabilistic Method to Explain Graph Neural Networks
by: Sloneker, Whitney, et al.
Published: (2024)

Explaining Graph Neural Networks via Structure-aware Interaction Index
by: Bui, Ngoc, et al.
Published: (2024)