# Fed-CausalDiff: Decoupled Synchronization for Federated Do-Simulation and Policy Evaluation

arXiv: https://arxiv.org/abs/2606.22510 · HTML: https://mlsanity.com/paper/2606.22510/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 21 Jun 2026.

## Builds on (most cited first, 21 of 21)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization](https://mlsanity.com/paper/2007.07481/) (2020)
- [Exploiting Shared Representations for Personalized Federated Learning](https://mlsanity.com/paper/2102.07078/) (2021)
- [Doubly Robust Off-policy Value Evaluation for Reinforcement Learning](https://mlsanity.com/paper/1511.03722/) (2015)
- [Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs](https://mlsanity.com/paper/1706.02633/) (2017)
- [Deep Knowledge Tracing](https://mlsanity.com/paper/1506.05908/) (2015)
- [Context-Aware Attentive Knowledge Tracing](https://mlsanity.com/paper/2007.12324/) (2020)
- [Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations](https://mlsanity.com/paper/2002.04083/) (2020)
- [A Review of Off-Policy Evaluation in Reinforcement Learning](https://mlsanity.com/paper/2212.06355/) (2022)
- [FedGAN: Federated Generative Adversarial Networks for Distributed Data](https://mlsanity.com/paper/2006.07228/) (2020)
- [Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation](https://mlsanity.com/paper/2008.07146/) (2020)
- [Causal Inference in Recommender Systems: A Survey and Future Directions](https://mlsanity.com/paper/2208.12397/) (2022)
- [Federated Causal Inference in Heterogeneous Observational Data](https://mlsanity.com/paper/2107.11732/) (2021)
- [Towards Practical Federated Causal Structure Learning](https://mlsanity.com/paper/2306.09433/) (2023)
- [Federated Learning for Diffusion Models](https://mlsanity.com/paper/2503.06426/) (2025)
- [Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy](https://mlsanity.com/paper/1808.00232/) (2018)
- [Federated Causal Inference: Multi-Study ATE Estimation beyond Meta-Analysis](https://mlsanity.com/paper/2410.16870/) (2024)
- [MULTI-FLGANs: Multi-Distributed Adversarial Networks for Non-IID distribution](https://mlsanity.com/paper/2206.12178/) (2022)
- [Federated Causal Inference from Multi-Site Observational Data via Propensity Score Aggregation](https://mlsanity.com/paper/2505.17961/) (2025)

## Abstract (arXiv)

While federated learning enables collaborative modelling on decentralised data, standard methods merely fit historical observations. This purely observational approach is fundamentally insufficient for interventional inference and policy evaluation, as sequential actions dynamically alter future states. We propose Fed-CausalDiff, a federated causal diffusion framework for do-simulation. The architecture decomposes the evolution of the latent state into a global causal score function and a local confounding score function. This design enables decoupled synchronisation (DSS), where clients aggregate only the shared causal mechanism while retaining site-specific confounders locally to handle heterogeneity. Experiments on four datasets demonstrate that Fed-CausalDiff achieves better ATE and policy-value estimation accuracy, offering a favorable trade-off between communication cost and inference fidelity.