# JANUS: Structured Bidirectional Generation for Guaranteed Constraints and Analytical Uncertainty

arXiv: https://arxiv.org/abs/2603.03748 · HTML: https://mlsanity.com/paper/2603.03748/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 46 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 24 of 24)

- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [DAGs with NO TEARS: Continuous Optimization for Structure Learning](https://mlsanity.com/paper/1803.01422/) (2018)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Deep Structural Causal Models for Tractable Counterfactual Inference](https://mlsanity.com/paper/2006.06485/) (2020)
- [CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training](https://mlsanity.com/paper/1709.02023/) (2017)
- [Uncertainty Quantification and Deep Ensembles](https://mlsanity.com/paper/2007.08792/) (2020)
- [DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks](https://mlsanity.com/paper/2110.12884/) (2021)
- [Causal Autoregressive Flows](https://mlsanity.com/paper/2011.02268/) (2020)
- [Bias in Machine Learning Software: Why? How? What to do?](https://mlsanity.com/paper/2105.12195/) (2021)
- [Diffusion Causal Models for Counterfactual Estimation](https://mlsanity.com/paper/2202.10166/) (2022)
- [Synthcity: facilitating innovative use cases of synthetic data in different data modalities](https://mlsanity.com/paper/2301.07573/) (2023)
- [Modeling Causal Mechanisms with Diffusion Models for Interventional and Counterfactual Queries](https://mlsanity.com/paper/2302.00860/) (2023)
- [VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queries](https://mlsanity.com/paper/2110.14690/) (2021)
- [CuTS: Customizable Tabular Synthetic Data Generation](https://mlsanity.com/paper/2307.03577/) (2023)
- [Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applications](https://mlsanity.com/paper/2309.13207/) (2023)
- [Synthetic Tabular Data: Methods, Attacks and Defenses](https://mlsanity.com/paper/2506.06108/) (2025)
- [Generation and Simulation of Synthetic Datasets with Copulas](https://mlsanity.com/paper/2203.17250/) (2022)
- [Differential Privacy Made Easy](https://mlsanity.com/paper/2201.00099/) (2022)
- [Generation and analysis of synthetic data via Bayesian networks: a robust approach for uncertainty quantification via Bayesian paradigm](https://mlsanity.com/paper/2402.17915/) (2024)
- [Bayesian CART models for aggregate claim modeling](https://mlsanity.com/paper/2409.01908/) (2024)

## Abstract (arXiv)

High-stakes synthetic data generation faces a fundamental Quadrilemma: achieving Fidelity to the original distribution, Control over complex logical constraints, Reliability in uncertainty estimation, and Efficiency in computational cost -- simultaneously. State-of-the-art Deep Generative Models (CTGAN, TabDDPM) excel at fidelity but rely on inefficient rejection sampling for continuous range constraints. Conversely, Structural Causal Models offer logical control but struggle with high-dimensional fidelity and complex noise inversion. We introduce JANUS (Joint Ancestral Network for Uncertainty and Synthesis), a framework that unifies these capabilities using a DAG of Bayesian Decision Trees. Our key innovation is Reverse-Topological Back-filling, an algorithm that propagates constraints backwards through the causal graph, achieving 100% constraint satisfaction on feasible constraint sets without rejection sampling. This is paired with an Analytical Uncertainty Decomposition derived from Dirichlet priors, enabling 128x faster uncertainty estimation than Monte Carlo methods. Across 15 datasets and 523 constrained scenarios, JANUS achieves state-of-the-art fidelity (Detection Score 0.497), eliminates mode collapse on imbalanced data, and provides exact handling of complex inter-column constraints (e.g., Salary_offered >= Salary_requested) where baselines fail entirely.