GenCO：生成具有组合约束的多样化设计
GenCO: Generating Diverse Designs with Combinatorial Constraints
AI总结：
GenCO框架通过可微组合求解器在训练中强制可行性，使深度生成模型在满足硬组合约束的同时生成多样化、高质量的设计方案。
摘要：
诸如GAN和VAE之类的深度生成模型在生成图像等无约束对象方面已展现出令人瞩目的成果。然而，在工业设计、材料科学、计算机图形学等领域中出现的许多设计场景，要求生成的对象除了对数据分布进行建模之外，还必须满足严格的组合约束或达到特定目标。为了解决这一问题，我们提出了GenCO，这是一个生成式框架，通过利用可微组合求解器来强制可行性，从而在整个训练过程中保证约束满足。GenCO将生成损失施加在可证明可行的解上，而不是中间的软解上，这意味着深度生成网络可以专注于确保生成的对象与数据分布相匹配，而无需同时捕捉可行性。这一转变使实践者能够在端到端训练期间对生成输出施加硬约束，从而能够评估其可行性，并将额外的组合损失分量引入深度生成训练中。我们在多种生成式组合任务上展示了该方法的有效性，包括游戏关卡生成、用于路径规划的地图创建以及光子器件设计，一致证明了其能够产出多样化、高质量且可验证地符合用户指定组合属性的解决方案。
英文摘要：
Deep generative models like GAN and VAE have shown impressive results in generating unconstrained objects like images. However, many design settings arising in industrial design, material science, computer graphics and more require that the generated objects satisfy hard combinatorial constraints or meet objectives in addition to modeling a data distribution. To address this, we propose GenCO, a generative framework that guarantees constraint satisfaction throughout training by leveraging differentiable combinatorial solvers to enforce feasibility. GenCO imposes the generative loss on provably feasible solutions rather than intermediate soft solutions, meaning that the deep generative network can focus on ensuring the generated objects match the data distribution without having to also capture feasibility. This shift enables practitioners to enforce hard constraints on the generated outputs during end-to-end training, enabling assessments of their feasibility and introducing additional combinatorial loss components to deep generative training. We demonstrate the effectiveness of our approach on a variety of generative combinatorial tasks, including game level generation, map creation for path planning, and photonic device design, consistently demonstrating its capability to yield diverse, high-quality solutions that verifiably adhere to user-specified combinatorial properties.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
