在不交换数据的前提下，让分散的数据源学会生成新组合，提升跨领域生成能力。
Compositional Generative Modeling from Decentralized Data
- 通过结构约束实现跨数据源的生成因子协同建模。
- 在图像生成、机器人规划等任务上显著优于联邦学习和专家混合模型。
- 适合需要隐私保护且需生成新组合的应用场景。
学习物理世界的组合特性需要联合观察相互作用的因素。然而，实际数据通常是分散的，这些因素被分割在孤立的数据孤岛中。现有的去中心化生成方法仅关注各孤岛数据的并集建模，忽略了由整体共同蕴含的新组合。为此，我们提出去中心化组合流匹配（DCFM）框架，在不交换任何原始数据的前提下，对全局生成因子施加结构约束。通过同伴交互，即使单个数据源无法独立支持某种组合，也能催生新组合。实验表明，DCFM 在条件图像生成、机器人空间规划及医疗属性共现建模任务上，显著优于联邦学习与专家混合基线。
原文摘要 · Abstract (English)
Learning the compositional nature of the physical world requires joint observation of interacting factors. However, because practical data is often decentralized, these factors are fragmented across isolated silos. Existing decentralized generative approaches focus only on modeling the union of siloed data, overlooking novel combinations implied by the collective whole. To bridge this gap, we introduce Decentralized Compositional Flow Matching (DCFM), a framework that enforces structural constraints across the global set of generative factors, without exchanging any raw data. DCFM enables novel combinations to emerge through peer interactions, even when no single data source can independently support the composition. Empirically, DCFM substantially outperforms federated learning and mixture-of-experts baselines across conditional image generation, robotic spatial planning, and medical attribute co-occurrence modeling.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。