通过表征学习实现条件扩散模型的高效迁移，大幅降低目标任务数据需求。
Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning
- 基于共享低维表征假设，利用源任务学习通用表征以支持迁移。
- 理论证明：良好表征可显著降低目标任务的样本复杂度。
- 适用于小样本场景下的图像生成等实际应用，具可解释性。
尽管条件扩散模型在诸多应用中取得了显著成果，但其从头训练需要大量数据，这在实践中往往不可行。为此，迁移学习成为小样本场景下的关键范式。尽管迁移学习在实践中表现成功，但其理论基础，特别是针对条件扩散模型的迁移效率，仍缺乏研究。本文首次从表征学习的角度，探索条件扩散模型迁移学习的样本效率。受实际训练流程启发，我们假设所有任务间存在共享的低维条件表征。分析表明，若能从源任务中学习到优良表征，则可显著降低目标任务的样本复杂度。此外，我们还探讨了理论结果在多个真实应用场景中的实践意义，并通过数值实验验证了结论。
原文摘要 · Abstract (English)
While conditional diffusion models have achieved remarkable success in various applications, they require abundant data to train from scratch, which is often infeasible in practice. To address this issue, transfer learning has emerged as an essential paradigm in small data regimes. Despite its empirical success, the theoretical underpinnings of transfer learning conditional diffusion models remain unexplored. In this paper, we take the first step towards understanding the sample efficiency of transfer learning conditional diffusion models through the lens of representation learning. Inspired by practical training procedures, we assume that there exists a low-dimensional representation of conditions shared across all tasks. Our analysis shows that with a well-learned representation from source tasks, the samplecomplexity of target tasks can be reduced substantially. In addition, we investigate the practical implications of our theoretical results in several real-world applications of conditional diffusion models. Numerical experiments are also conducted to verify our results.
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。