用主模型损失引导辅助生成，解决流模型模式崩溃问题
Loss-Guided Auxiliary Agents for Overcoming Mode Collapse in GFlowNets
- 让辅助生成网络根据主模型损失高低选择探索路径
- 在序列生成任务中发现超40倍的唯一有效模式
- 适合需要多样生成结果的复杂场景如生物序列设计
虽然生成流网络（GFlowNets）旨在捕捉奖励函数的多个模式，但在实际应用中常出现模式崩溃，陷入早期发现的模式而难以找到多样解，需长时间训练。现有探索方法多依赖启发式新颖性信号。本文提出损失引导的生成流网络（LGGFN），其辅助生成网络的探索直接由主模型训练损失驱动。通过优先采样主模型损失较高的轨迹，LGGFN聚焦于状态空间中理解不足的区域，显著加速多样高回报样本的发现。在网格环境、结构化序列生成、贝叶斯结构学习及生物序列设计等多样化基准上，LGGFN始终优于基线，在探索效率与样本多样性方面表现突出。例如，在一项具有挑战性的序列生成任务中，它发现了超过40倍的唯一有效模式，同时将探索误差指标降低约99%。
原文摘要 · Abstract (English)
Although Generative Flow Networks (GFlowNets) are designed to capture multiple modes of a reward function, they often suffer from mode collapse in practice, getting trapped in early-discovered modes and requiring prolonged training to find diverse solutions. Existing exploration techniques often rely on heuristic novelty signals. We propose Loss-Guided GFlowNets (LGGFN), a novel approach where an auxiliary GFlowNet's exploration is \textbf{directly driven by the main GFlowNet's training loss}. By prioritizing trajectories where the main model exhibits \textbf{high loss}, LGGFN focuses sampling on poorly understood regions of the state space. This targeted exploration significantly accelerates the discovery of diverse, high-reward samples. Empirically, across \textbf{diverse benchmarks} including grid environments, structured sequence generation, Bayesian structure learning, and biological sequence design, LGGFN consistently \textbf{outperforms} baselines in exploration efficiency and sample diversity. For instance, on a challenging sequence generation task, it discovered over 40 times more unique valid modes while simultaneously reducing the exploration error metric by approximately 99\%.
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。