# Adversarial Causal Tuning for Realistic Time-series Generation

arXiv: https://arxiv.org/abs/2506.02084 · HTML: https://mlsanity.com/paper/2506.02084/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 44 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 19 of 19)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Revisiting Classifier Two-Sample Tests](https://mlsanity.com/paper/1610.06545/) (2016)
- [Differentiable Causal Discovery from Interventional Data](https://mlsanity.com/paper/2007.01754/) (2020)
- [DYNOTEARS: Structure Learning from Time-Series Data](https://mlsanity.com/paper/2002.00498/) (2020)
- [TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation](https://mlsanity.com/paper/2111.08095/) (2021)
- [Synthcity: facilitating innovative use cases of synthetic data in different data modalities](https://mlsanity.com/paper/2301.07573/) (2023)
- [A Survey on Causal Discovery: Theory and Practice](https://mlsanity.com/paper/2305.10032/) (2023)
- [CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discovery](https://mlsanity.com/paper/2310.01753/) (2023)
- [FECAM: Frequency Enhanced Channel Attention Mechanism for Time Series Forecasting](https://mlsanity.com/paper/2212.01209/) (2022)
- [Bootstrapping the Out-of-sample Predictions for Efficient and Accurate Cross-Validation](https://mlsanity.com/paper/1708.07180/) (2017)
- [Sequential Models in the Synthetic Data Vault](https://mlsanity.com/paper/2207.14406/) (2022)
- [Embracing the black box: Heading towards foundation models for causal discovery from time series data](https://mlsanity.com/paper/2402.09305/) (2024)
- [Towards Automated Causal Discovery: a case study on 5G telecommunication data](https://mlsanity.com/paper/2402.14481/) (2024)

## Built on by (most cited first, 3 of 3)

- [Causal Reflection with Language Models](https://mlsanity.com/paper/2508.04495/) (2025)
- [Large Causal Models for Temporal Causal Discovery](https://mlsanity.com/paper/2602.18662/) (2026)
- [Adversarial Causal Intervention Falsification](https://mlsanity.com/paper/2608.06427/) (2026)

## Abstract (arXiv)

We address the problem of generating simulated, yet realistic, time-series data from a causal model with the same observational and interventional distributions as a given real dataset (probabilistic causal digital twin). While non-causal models (e.g., GANs) also strive to simulate realistic data, causal models are fundamentally more powerful, able to simulate the effect of interventions (what-if scenarios), optimize decisions, perform root-cause analysis, and counterfactual causal reasoning. We introduce the Adversarial Causal Tuning (ACT) methodology, which outputs the optimal causal model that fits the data, along with a quantification of the goodness-of-fit. The returned causal model can then be employed to simulate new data or to perform other causal reasoning tasks. ACT adopts ideas from Generative Adversarial Network training and AutoML to search for optimal causal pipelines and discriminators that detect deviations between the distributions of real and simulated data. It also adapts a permutation testing procedure from established causal tuning methods to penalize models for complexity. Through extensive experiments on real, semi-synthetic, and synthetic datasets, we show that (a) employing multiple optimized discriminators is paramount for selecting the optimal causal models and quantifying goodness-of-fit, (b) ACT selects the optimal causal model in synthetic datasets while avoiding overfitting, generating data indistinguishable from the true data distribution (c) all state-of-the-art generative and causal simulation methods, exhibit room for improvement in reproducing real data distributions; generating realistic temporal data is still an open research challenge.