Diffusion Models with Double Guidance: Generate with aggregated datasets
This addresses a practical challenge for researchers and practitioners in generative AI who need to merge datasets with incomplete annotations, though it is incremental as it builds on existing diffusion models.
The paper tackles the problem of conditional generative modeling with aggregated datasets that have inconsistent attributes, leading to missing conditions, by proposing a Diffusion Model with Double Guidance that enables precise generation without requiring joint annotations. It demonstrates effectiveness in molecular and image generation, outperforming baselines in alignment and controllability.
Creating large-scale datasets for training high-performance generative models is often prohibitively expensive, especially when associated attributes or annotations must be provided. As a result, merging existing datasets has become a common strategy. However, the sets of attributes across datasets are often inconsistent, and their naive concatenation typically leads to block-wise missing conditions. This presents a significant challenge for conditional generative modeling when the multiple attributes are used jointly as conditions, thereby limiting the model's controllability and applicability. To address this issue, we propose a novel generative approach, Diffusion Model with Double Guidance, which enables precise conditional generation even when no training samples contain all conditions simultaneously. Our method maintains rigorous control over multiple conditions without requiring joint annotations. We demonstrate its effectiveness in molecular and image generation tasks, where it outperforms existing baselines both in alignment with target conditional distributions and in controllability under missing condition settings.