arXiv cs.AI· Yiming Yao, Liang Zhao, Qingfu Zhang·· 2 天前AI 评分22
ICPSL：从有限离线数据进行上下文偏好条件化 Pareto 集学习
In-Context Preference-Conditioned Pareto Set Learning from Limited Offline Data
AI 导读
研究者提出上下文偏好条件化 Pareto 集学习框架 ICPSL，通过在大量合成先验数据上预训练基础式超网络，使其在给定未见问题的离线观测后，单次前向传播即可生成该问题的偏好条件化 Pareto 解模型。生成的模型可复用于任意偏好预测解，无需针对具体问题训练或逐偏好搜索，在合成与真实问题上均生成高质量 Pareto 解并大幅加速问题特定解模型的构建。
正文 · 原文
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.21736 [cs.AI] |
| (or arXiv:2610.21736v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21736 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yiming Yao [view email]
[v1]
Thu, 15 Oct 2026 11:54:43 UTC (237 KB)
来源：arXiv cs.AI · arxiv.org