Diffusion models have emerged as powerful generative tools, rivaling GANs in sample quality and mirroring the likelihood scores of autoregressive models. A subset of these models, exemplified by DDIMs, exhibit an inherent asymmetry: they are trained over $T$ steps but only sample from a subset of $T$ during generation. This selective sampling approach, though optimized for speed, inadvertently misses out on vital information from the unsampled steps, leading to potential compromises in sample quality. To address this issue, we present the S$^{2}$-DMs, which is a new training method by using an innovative $L_{skip}$, meticulously designed to reintegrate the information omitted during the selective sampling phase. The benefits of this approach are manifold: it notably enhances sample quality, is exceptionally simple to implement, requires minimal code modifications, and is flexible enough to be compatible with various sampling algorithms. On the CIFAR10 dataset, models trained using our algorithm showed an improvement of 3.27% to 14.06% over models trained with traditional methods across various sampling algorithms (DDIMs, PNDMs, DEIS) and different numbers of sampling steps (10, 20, ..., 1000). On the CELEBA dataset, the improvement ranged from 8.97% to 27.08%. Access to the code and additional resources is provided in the github.

翻译：扩散模型已成为强大的生成工具，在样本质量上可与生成对抗网络（GANs）相媲美，在似然分数上可媲美自回归模型。以DDIMs为代表的一类扩散模型存在固有非对称性：它们基于$T$步训练，但在生成过程中仅从$T$的子集采样。这种选择性采样方法虽可优化速度，但不可避免地丢失了未采样步骤的关键信息，可能导致样本质量下降。为解决该问题，我们提出S$^{2}$-DMs，这是一种采用创新性$L_{skip}$的新训练方法，其精心设计以重新整合选择性采样阶段遗漏的信息。该方法具有多重优势：显著提升样本质量、实现极其简单、所需代码修改极少，且足够灵活以兼容多种采样算法。在CIFAR10数据集上，采用我们算法训练的模型在多种采样算法（DDIMs、PNDMs、DEIS）及不同采样步数（10, 20, ..., 1000）下，较传统方法训练的模型提升3.27%至14.06%。在CELEBA数据集上，改进幅度达8.97%至27.08%。代码及其他资源可在GitHub获取。