Compositional Generative Modeling from Decentralized Data
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Conditional Image GenerationFederated LearningSimilar Papers 제목 키워드 기반
Achieving Linear Speedup in Decentralized Stochastic Compositional Minimax Optimization
The stochastic compositional minimax problem has attracted a surge of attention in recent years since it covers many emerging machine learning models. Meanwhile, due to the emergence of distributed data, optimizing this …
imbalanced classificationCompositional Flows for 3D Molecule and Synthesis Pathway Co-design
Many generative applications, such as synthesis-based 3D molecular design, involve constructing compositional objects with continuous features. Here, we introduce Compositional Generative Flows (CGFlow), a novel framewor…
Drug DesignCompositional Generative Modeling: A Single Model is Not All You Need
Large monolithic generative models trained on massive amounts of data have become an increasingly dominant approach in AI research. In this paper, we argue that we should instead construct large generative systems by com…
AllDecentralized Multi-Level Compositional Optimization Algorithms with Level-Independent Convergence Rate
Stochastic multi-level compositional optimization problems cover many new machine learning paradigms, e.g., multi-step model-agnostic meta-learning, which require efficient optimization algorithms for large-scale data. T…
Meta-LearningFast Training Method for Stochastic Compositional Optimization Problems
The stochastic compositional optimization problem covers a wide range of machine learning models, such as sparse additive models and model-agnostic meta-learning. Thus, it is necessary to develop efficient methods for i…
Additive modelsMeta-Learning