Yao, Y., Pan, Y., Li, J., Tsang, I., & Yao, X. (2024). PROUD: PaRetO-gUided diffusion model for multi-objective generation. Machine Learning, 113(9), 6511–6538. https://doi.org/10.1007/s10994-024-06575-2
Abstract:
Recent advancements in the realm of deep generative models focus on generating samples that satisfy multiple desired properties. However, prevalent approaches optimize these property functions independently, thus omitting the trade-ofs among them. In addition, the property optimization is often improperly integrated into the generative models, resulting in an unnecessary compromise on generation quality (i.e., the quality of generated samples). To address these issues, we formulate a constrained optimization problem. It seeks to optimize generation quality while ensuring that generated samples reside at the Pareto front of multiple property objectives. Such a formulation enables the generation of samples that cannot be further improved simultaneously on the conficting property functions and preserves good quality of generated samples.Building upon this formulation, we introduce the ParetO-gUided Difusion model (PROUD), wherein the gradients in the denoising process are dynamically adjusted to enhance generation quality while the generated samples adhere to Pareto optimality. Experimental evaluations on image generation and protein generation tasks demonstrate that our PROUD consistently maintains superior generation quality while approaching Pareto optimality across multiple property functions compared to various baselines.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Agency for Science, Technology and Research - Career Development Fund
Grant Reference no. : C222812019
This research / project is supported by the Agency for Science, Technology and Research - Pitchfest for ECR
Grant Reference no. : 232D800027
This research / project is supported by the Agency for Science, Technology and Research - GAP Project
Grant Reference no. : I23D1AG079
This research / project is supported by the National Research Foundation - AI Singapore Programme
Grant Reference no. : AISG2-GC-2023-010-T
This work was partially supported by the Program for Guangdong Introducing Innovative and Entrepreneurial Teams
This work was partially supported by the Program for Guangdong Provincial Key Laboratory.
This research / project is supported by the Ministry of Science and Technology (MOST) of CHINA - National Natural Science Foundation of China (NSFC)
Grant Reference no. : 62250710682
Description:
This is a post-peer-review, pre-copyedit version of an article published in Machine Learning. The final authenticated version is available online at: http://dx.doi.org/10.1007/s10994-024-06575-2