Imagen de Portada

Posterior-Calibrated Causal Circuits in Variational Autoencoders: Why Image-Domain Interpretability Fails on Tabular Data

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Roy, Dip, Misra, Rajiv, Singh, Sanjay Kumar, Roy, Anisha
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A Multi-Level Causal Intervention Framework for Mechanistic Interpretability in Variational Autoencoders
por: Roy, Dip, et al.
Publicado: (2025)

Detection Without Correction: A Robust Asymmetry in Activation-Based Hallucination Probing
por: Roy, Dip, et al.
Publicado: (2026)

Fundamental Limits of Neural Network Sparsification: Evidence from Catastrophic Interpretability Collapse
por: Roy, Dip, et al.
Publicado: (2026)

MemGuard-Alpha: Detecting and Filtering Memorization-Contaminated Signals in LLM-Based Financial Forecasting via Membership Inference and Cross-Model Disagreement
por: Roy, Anisha, et al.
Publicado: (2026)

Bayesian Autoencoder for Medical Anomaly Detection: Uncertainty-Aware Approach for Brain 2 MRI Analysis
por: Roy, Dip
Publicado: (2025)

Mechanistic Interpretability of Diffusion Models: Circuit-Level Analysis and Causal Validation
por: Roy, Dip
Publicado: (2025)

Variational Autoencoder for Calibration: A New Approach
por: Barrett, Travis, et al.
Publicado: (2025)

ARDDQN: Attention Recurrent Double Deep Q-Network for UAV Coverage Path Planning and Data Harvesting
por: Kumar, Praveen, et al.
Publicado: (2024)

CardiCat: a Variational Autoencoder for High-Cardinality Tabular Data
por: Carlin, Lee, et al.
Publicado: (2025)

XNNTab -- Interpretable Neural Networks for Tabular Data using Sparse Autoencoders
por: Elhadri, Khawla, et al.
Publicado: (2025)

Exploring Transformer Placement in Variational Autoencoders for Tabular Data Generation
por: Silva, Aníbal, et al.
Publicado: (2026)

Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders
por: Dang, Hien, et al.
Publicado: (2023)

Posterior Collapse as a Phase Transition in Variational Autoencoders
por: Li, Zhen, et al.
Publicado: (2025)

A Latent Space Correlation-Aware Autoencoder for Anomaly Detection in Skewed Data
por: Roy, Padmaksha
Publicado: (2023)

Causal Dynamic Variational Autoencoder for Counterfactual Regression in Longitudinal Data
por: Bouchattaoui, Mouad El, et al.
Publicado: (2023)

Why Domain Generalization Fail? A View of Necessity and Sufficiency
por: Vuong, Long-Tung, et al.
Publicado: (2025)

Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders
por: Yacoby, Yaniv, et al.
Publicado: (2024)

Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation
por: Pacela, Vitória Barin, et al.
Publicado: (2026)

Table2Image: Interpretable Tabular Data Classification with Realistic Image Transformations
por: Lee, Seungeun, et al.
Publicado: (2024)

Quantum Generative Adversarial Autoencoders: Learning latent representations for quantum data generation
por: Raj, Naipunnya, et al.
Publicado: (2025)

Interpretable Mesomorphic Networks for Tabular Data
por: Kadra, Arlind, et al.
Publicado: (2023)

Interpretable Deep Clustering for Tabular Data
por: Svirsky, Jonathan, et al.
Publicado: (2023)

Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization
por: Zhang, Zheyuan, et al.
Publicado: (2026)

Diffusion-Scheduled Denoising Autoencoders for Anomaly Detection in Tabular Data
por: Sattarov, Timur, et al.
Publicado: (2025)

Posterior Sampling for Continuing Environments
por: Xu, Wanqiao, et al.
Publicado: (2022)

Synthetic Tabular Data Generation for Class Imbalance and Fairness: A Comparative Study
por: Panagiotou, Emmanouil, et al.
Publicado: (2024)

Efficient and Interpretable Information Retrieval for Product Question Answering with Heterogeneous Data
por: Biswas, Biplob, et al.
Publicado: (2024)

FlagGAM: Rule-Based Generalized Additive Modeling for Explainable Tabular Prediction
por: Zhao, Zijie, et al.
Publicado: (2026)

To Predict or Not To Predict? Proportionally Masked Autoencoders for Tabular Data Imputation
por: Kim, Jungkyu, et al.
Publicado: (2024)

Data-efficient and Interpretable Inverse Materials Design using a Disentangled Variational Autoencoder
por: Zeng, Cheng, et al.
Publicado: (2024)

CausalWrap: Model-Agnostic Causal Constraint Wrappers for Tabular Synthetic Data
por: Asiaee, Amir, et al.
Publicado: (2026)

Interpretable Graph Neural Networks for Heterogeneous Tabular Data
por: Alkhatib, Amr, et al.
Publicado: (2024)

Towards Interpretable Deep Neural Networks for Tabular Data
por: Elhadri, Khawla, et al.
Publicado: (2025)

Stable Coresets via Posterior Sampling: Aligning Induced and Full Loss Landscapes
por: Chang, Wei-Kai, et al.
Publicado: (2025)

Causal Posterior Estimation
por: Dirmeier, Simon, et al.
Publicado: (2025)

Data Augmentation with Variational Autoencoder for Imbalanced Dataset
por: Stocksieker, Samuel, et al.
Publicado: (2024)

Interpretable Graph Neural Networks for Tabular Data
por: Alkhatib, Amr, et al.
Publicado: (2023)

Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders
por: O'Neill, Charles, et al.
Publicado: (2025)

Data-Driven Generation of Neutron Star Equations of State Using Variational Autoencoders
por: Ross, Alex, et al.
Publicado: (2026)

Exponential Family Variational Flow Matching for Tabular Data Generation
por: Guzmán-Cordero, Andrés, et al.
Publicado: (2025)