Guided Data Generation for Understanding Model Behavior
cs.LG
Submitted: 2025-02-10
Updated: 2026-08-27
Code: https://github.com/madebyollin/taesd
License: http://creativecommons.org/licenses/by/4.0/
The gist: We propose a method for generating distributions over the input space as an inspection tool for understanding trained models.
Terminology
Abstract
We propose a method for generating distributions over the input space as an inspection tool for understanding trained models. Our framework poses questions of the form ``which inputs would make a trained model exhibit a specified behavior?'' and encodes each question through a guidance function. The generated data provide insights into how the models behave. To showcase our framework, we pose queries such as generating distributions of data where a specified label would be predicted by the model, where two distinct models would disagree, where the output is sensitive to parameter perturbations, and where predictions would be risky. Our method can be applied with a variety of classification and regression tasks and on a range of model types.
Sources
- Data augmentation using synthetic data for time series classification with deep residual networks
- An Introduction to Variational Inference
- Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
- TabPFGen -- Tabular Data Generation with TabPFN
- TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks