发表机构
Fuzhou University; Imperial College London; National University of Singapore（福州大学; 伦敦帝国学院; 新加坡国立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究神经集函数学习，针对现有最优子集预言机框架依赖蒙特卡罗采样估计梯度导致计算开销大且轨迹不稳定的问题，提出将证据下界重新解释为连续松弛并学习替代目标，实验证明该方法能减少开销、加速推理并优于现有基线。
AI 中文摘要
学习神经集函数对包括人工智能驱动的药物发现中的化合物选择和产品推荐在内的广泛重要应用至关重要。近期工作引入了最优子集预言机，在实际弱监督设置下隐式学习集函数，通过平均场变分推理优化模型参数。然而，这些框架在更新变分分布时依赖蒙特卡罗采样估计证据下界梯度。跨迭代重复采样会产生大量计算开销，且随机性会使优化轨迹不稳定。本文将证据下界重新解释为集函数的连续松弛，并学习一个替代目标，在变分优化期间取代基于采样的ELBO梯度估计。学习到的替代目标在整个连续域提供稳定高效的梯度，从而减少计算开销并加速推理。此外，我们为所提出框架在次模最大化下建立了近似保证，并刻画了其与变分自由能的联系。在各种实际任务上的实验表明，相对于现有基线有持续改进。
英文摘要
Learning neural set functions is pivotal to a wide range of important applications, including compound selection in AI-driven drug discovery and product recommendation. Recent work has introduced optimal subset oracles to implicitly learn set functions under practical weakly supervised settings, where model parameters are optimized through mean-field variational inference. However, these frameworks rely on Monte Carlo sampling to estimate gradients of the evidence lower bound when updating the variational distribution. Repeated sampling across iterations incurs substantial computational overhead, while the resulting stochasticity can destabilize the optimization trajectory. In this work, we reinterpret the evidence lower bound as a continuous relaxation of the set function and learn a surrogate objective that replaces sampling-based ELBO gradient estimation during variational optimization. The learned surrogate provides stable and efficient gradients throughout the continuous domain, thereby reducing computational overhead and accelerating inference. Furthermore, we establish an approximation guarantee for the proposed framework under submodular maximization and characterize its connection to variational free energy. Experiments on a variety of real-world tasks demonstrate consistent improvements over existing baselines.
