Posterior-calibrated causal circuits in variational autoencoders: why image-domain interpretability fails on tabular data
- 1 August 2026
- journal article
- research article
- Published by Springer Nature in Neural Computing and Applications
- Vol. 38 (15) , 610
Abstract
No abstract availableKeywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Causal Intervention Framework for Variational Auto Encoder Mechanistic InterpretabilityResearch Square, 2025
- Towards Automated Circuit Discovery for Mechanistic Interpretability2023
- Locating and Editing Factual Associations in GPT2022
- CausalVAE: Disentangled Representation Learning via Neural Structural Causal Models2021
- Feature VisualizationDistill, 2017
- Network Dissection: Quantifying Interpretability of Deep Visual Representations2017
- A data-driven approach to predict the success of bank telemarketingDecision Support Systems, 2014
- Modeling wine preferences by data mining from physicochemical propertiesDecision Support Systems, 2009
- Causality2009
- The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clientsExpert Systems with Applications, 2009