无需重训即可快速组合多目标生成，提升科学发现效率。
Routing by Reaching: Composition of Pre-trained GFlowNets for Multi-Objective Generation
- 推理时组合预训练GFlowNets，动态适应新目标组合。
- 线性加权目标下精确恢复目标分布，非线性时有误差量化。
- 适合需频繁切换目标的分子生成等科学探索场景。
生成流网络（GFlowNets）能按奖励函数比例采样多样化候选解，非常适合科学发现中探索多种潜在解决方案。将GFlowNets扩展至多目标设置日益受到关注，因现实应用常涉及多个冲突目标。然而，现有方法需为每组目标联合训练，目标变化即需从头再训练。本文提出一种在推理时组合预训练GFlowNets的框架，实现无需微调或重训的快速适应。该框架灵活，可处理从线性加权到复杂非线性算子的各种奖励组合，而此前方法常需单独处理。我们证明该方法在线性加权下能精确恢复目标分布，并通过畸变因子量化非线性算子下的近似质量。在二维网格和真实分子生成任务上的实验表明，本方法性能与基线相当。
原文摘要 · Abstract (English)
Generative Flow Networks (GFlowNets) learn to sample diverse candidates in proportion to a reward function, making them well-suited for scientific discovery, where exploring multiple promising solutions is crucial. Further extending GFlowNets to multi-objective settings has attracted growing interest as real-world applications often involve multiple, conflicting objectives. However, existing approaches require joint training for each combination of objectives, meaning that any change in the objective set necessitates retraining from scratch. We propose a framework that composes pre-trained GFlowNets at inference time, enabling rapid adaptation without fine-tuning or retraining. Importantly, our framework is flexible, capable of handling diverse reward combinations ranging from linear scalarization to complex nonlinear operators, which are often handled separately in previous literature. We prove that our method exactly recovers the target distribution for linear scalarization, and quantify the approximation quality for nonlinear operators through a distortion factor. Experiments on a synthetic 2D grid and real-world molecule generation tasks demonstrate that our approach achieves performance comparable to baselines.
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。