arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.21736cs.AI
收藏

基于有限离线数据的上下文偏好条件帕累托集学习

In-Context Preference-Conditioned Pareto Set Learning from Limited Offline Data

City University of Hong Kong(香港城市大学)

Yiming Yao, Liang Zhao, Qingfu Zhang

AI总结:

本文提出ICPSL框架,基于有限离线数据,通过预训练超网络单次前向生成特定问题的偏好条件帕累托解模型,可快速预测任意偏好的高质量帕累托解,提升了模型构建速度。

摘要:

多目标优化涉及对冲突目标的不同偏好,偏好条件帕累托集学习并非返回一组有限的权衡解,而是将指定偏好直接映射到对应的帕累托最优解。然而在许多现实场景中,优化必须在无进一步目标评估的离线环境下进行,仅剩下稀疏覆盖决策空间和目标空间的有限静态数据集。现有方法要么针对每种偏好单独优化,要么训练特定问题的帕累托解模型,需要跨偏好重复搜索或跨问题重复训练。我们提出上下文偏好条件帕累托集学习(ICPSL)框架,该框架同时分摊偏好相关解搜索和特定问题模型构建的成本。ICPSL在大量多样的合成先验数据上预训练基础风格超网络,给定未知问题的离线观测数据后,预训练超网络可通过单次前向传播生成特定问题的偏好条件帕累托解模型,生成的模型可重复用于预测任意偏好的解,无需特定问题训练或跨偏好搜索。在合成及现实问题上的实验表明,ICPSL能生成高质量帕累托解,同时大幅加快特定问题解模型的构建速度。

英文摘要:

Multi-objective optimization involves diverse preferences over conflicting objectives. Rather than returning a finite set of trade-off solutions, preference-conditioned Pareto set learning seeks to map a specified preference directly to a corresponding Pareto optimal solution. Yet in many real-world scenarios, optimization must proceed offline without further objective evaluations, leaving only a limited static dataset that sparsely covers the decision and objective spaces. Existing methods either optimize separately for each preference or train a problem-specific Pareto solution model, requiring repeated search across preferences or repeated training across problems. We introduce in-context preference-conditioned Pareto set learning (ICPSL), a framework that amortizes both preference-wise solution search and problem-specific model construction. ICPSL pretrains a foundation-style hypernetwork on a large and diverse set of synthetic prior data. Given the offline observations of an unseen problem, the pretrained hypernetwork learns to generate a problem-specific, preference-conditioned Pareto solution model in a single forward pass. The generated model can then be reused to predict solutions for arbitrary preferences without problem-specific training or preference-wise search. Experiments on synthetic and real-world problems show that ICPSL produces high-quality Pareto solutions while providing substantial speedups in problem-specific solution-model construction.

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。

↑