# SiloFuse: Cross-silo Synthetic Data Generation with Latent Tabular Diffusion Models

arXiv: https://arxiv.org/abs/2404.03299 · HTML: https://mlsanity.com/paper/2404.03299/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 26 of its 53 references that are in the map.
- First posted on arXiv 4 Apr 2024.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)

## Builds on (most cited first, 26 of 26)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions](https://mlsanity.com/paper/2102.05379/) (2021)
- [Split learning for health: Distributed deep learning without sharing raw patient data](https://mlsanity.com/paper/1812.00564/) (2018)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models](https://mlsanity.com/paper/2103.04922/) (2021)
- [Data Synthesis based on Generative Adversarial Networks](https://mlsanity.com/paper/1806.03384/) (2018)
- [Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption](https://mlsanity.com/paper/1711.10677/) (2017)
- [CTAB-GAN: Effective Table Data Synthesizing](https://mlsanity.com/paper/2102.08369/) (2021)
- [STaSy: Score-based Tabular data Synthesis](https://mlsanity.com/paper/2210.04018/) (2022)
- [TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data](https://mlsanity.com/paper/2211.06550/) (2022)
- [Vertical Federated Learning: Challenges, Methodologies and Experiments](https://mlsanity.com/paper/2202.04309/) (2022)
- [A Unified Framework for Quantifying Privacy Risk in Synthetic Data](https://mlsanity.com/paper/2211.10459/) (2022)
- [Relational Data Synthesis using Generative Adversarial Networks: A Design Space Exploration](https://mlsanity.com/paper/2008.12763/) (2020)
- [dpart: Differentially Private Autoregressive Tabular, a General Framework for Synthetic Data Generation](https://mlsanity.com/paper/2207.05810/) (2022)
- [Privacy-preserving Data Sharing on Vertically Partitioned Data](https://mlsanity.com/paper/2010.09293/) (2020)
- [VT-GAN: Cooperative Tabular Data Synthesis using Vertical Federated Learning](https://mlsanity.com/paper/2302.01706/) (2023)

## Built on by (most cited first, 10 of 10)

- [Diffusion and Flow Matching Models for Tabular Data: A Survey](https://mlsanity.com/paper/2502.17119/) (2025)
- [WaveStitch: Flexible and Fast Conditional Time Series Generation with Diffusion Models](https://mlsanity.com/paper/2503.06231/) (2025)
- [GReaTER: Generate Realistic Tabular data after data Enhancement and Reduction](https://mlsanity.com/paper/2503.15564/) (2025)
- [TimeWak: Temporal Chained-Hashing Watermark for Time Series Data](https://mlsanity.com/paper/2506.06407/) (2025)
- [Towards Active Participant Centric Vertical Federated Learning: Some Representations May Be All You Need](https://mlsanity.com/paper/2410.17648/) (2024)
- [DEREC-SIMPRO: unlock Language Model benefits to advance Synthesis in Data Clean Room](https://mlsanity.com/paper/2411.00879/) (2024)
- [Federated Time Series Generation on Feature and Temporally Misaligned Data](https://mlsanity.com/paper/2410.21072/) (2024)
- [End to End Collaborative Synthetic Data Generation](https://mlsanity.com/paper/2412.03766/) (2024)
- [Limited Reference, Reliable Generation: A Two-Component Framework for Tabular Data Generation in Low-Data Regimes](https://mlsanity.com/paper/2509.09960/) (2025)
- [Harpoon: Generalised Manifold Guidance for Conditional Tabular Diffusion](https://mlsanity.com/paper/2602.07875/) (2026)

## Abstract (arXiv)

Synthetic tabular data is crucial for sharing and augmenting data across silos, especially for enterprises with proprietary data. However, existing synthesizers are designed for centrally stored data. Hence, they struggle with real-world scenarios where features are distributed across multiple silos, necessitating on-premise data storage. We introduce SiloFuse, a novel generative framework for high-quality synthesis from cross-silo tabular data. To ensure privacy, SiloFuse utilizes a distributed latent tabular diffusion architecture. Through autoencoders, latent representations are learned for each client's features, masking their actual values. We employ stacked distributed training to improve communication efficiency, reducing the number of rounds to a single step. Under SiloFuse, we prove the impossibility of data reconstruction for vertically partitioned synthesis and quantify privacy risks through three attacks using our benchmark framework. Experimental results on nine datasets showcase SiloFuse's competence against centralized diffusion-based synthesizers. Notably, SiloFuse achieves 43.8 and 29.8 higher percentage points over GANs in resemblance and utility. Experiments on communication show stacked training's fixed cost compared to the growing costs of end-to-end training as the number of training iterations increases. Additionally, SiloFuse proves robust to feature permutations and varying numbers of clients.