# Expert-Data Alignment Governs Generation Quality in Decentralized Diffusion Models

arXiv: https://arxiv.org/abs/2602.02685 · HTML: https://mlsanity.com/paper/2602.02685/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 27 of its 32 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 27 of 27)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Mixture-of-Experts with Expert Choice Routing](https://mlsanity.com/paper/2202.09368/) (2022)
- [Lipschitz regularity of deep neural networks: analysis and efficient estimation](https://mlsanity.com/paper/1805.10965/) (2018)
- [Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks](https://mlsanity.com/paper/1906.04893/) (2019)
- [Exactly Computing the Local Lipschitz Constant of ReLU Networks](https://mlsanity.com/paper/2003.01219/) (2020)
- [StableMoE: Stable Routing Strategy for Mixture of Experts](https://mlsanity.com/paper/2204.08396/) (2022)
- [Scaling Diffusion Transformers to 16 Billion Parameters](https://mlsanity.com/paper/2407.11633/) (2024)
- [EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing](https://mlsanity.com/paper/2410.02098/) (2024)
- [DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers](https://mlsanity.com/paper/2503.14487/) (2025)
- [Lipschitz Singularities in Diffusion Models](https://mlsanity.com/paper/2306.11251/) (2023)
- [Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation](https://mlsanity.com/paper/2510.09094/) (2025)
- [Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts](https://mlsanity.com/paper/2503.16057/) (2025)
- [Decentralized Diffusion Models](https://mlsanity.com/paper/2501.05450/) (2025)
- [Efficient Training of Diffusion Mixture-of-Experts Models: A Practical Recipe](https://mlsanity.com/paper/2512.01252/) (2025)
- [STORK: Faster Diffusion And Flow Matching Sampling By Resolving Both Stiffness And Structure-Dependence](https://mlsanity.com/paper/2505.24210/) (2025)
- [Paris: A Decentralized Trained Open-Weight Diffusion Model](https://mlsanity.com/paper/2510.03434/) (2025)

## Built on by (most cited first, 1 of 1)

- [Paris 2.0: A Decentralized Diffusion Model for Video Generation](https://mlsanity.com/paper/2605.26064/) (2026)

## Abstract (arXiv)

Decentralized Diffusion Models (DDMs) route denoising through experts trained independently on disjoint data clusters, which can strongly disagree in their predictions. What governs the quality of generations in such systems? We present the first ever systematic investigation of this question. A priori, the expectation is that minimizing denoising trajectory sensitivity -- minimizing how perturbations amplify during sampling -- should govern generation quality. We demonstrate this hypothesis is incorrect: a stability-quality dissociation. Full ensemble routing, which combines all expert predictions at each step, achieves the most stable sampling dynamics and best numerical convergence while producing the worst generation quality (FID 47.9 vs. 22.6 for sparse Top-2 routing). Instead, we identify expert-data alignment as the governing principle: generation quality depends on routing inputs to experts whose training distribution covers the current denoising state. Across two distinct DDM systems, we validate expert-data alignment using (i) data-cluster distance analysis, confirming sparse routing selects experts with data clusters closest to the current denoising state, and (ii) per-expert analysis, showing selected experts produce more accurate predictions than non-selected ones, and (iii) expert disagreement analysis, showing quality degrades when experts disagree. For DDM deployment, our findings establish that routing should prioritize expert-data alignment over numerical stability metrics.