arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.14550cs.LG
收藏

学习排序:任务序列作为上下文优化

Learning to Order: Task Sequencing as In-Context Optimization

Jan Kobiolka, Christian Frey, Arlind Kadra, Gresa Shala, Josif Grabocka

AI总结:

本文提出通过元学习方法解决任务序列排序问题,证明深度神经网络能从合成数据中学习到最优任务序列,实现少样本泛化。

摘要:

任务序列(TS)是深度学习中的核心开放问题,出现在机器人装配线和自动驾驶等多个现实领域。然而,以往的工作未能有效展示元学习的TS方法在解决新TS问题时的泛化能力,尤其是在初始示例有限的情况下。本文证明深度神经网络能够元学习无限先验的合成TS问题,并实现少样本泛化。我们元学习了一种基于Transformer的架构,该架构在由先验分布生成的序列轨迹数据集上进行训练,将任务序列作为有向图中的路径进行采样。在大规模实验中,我们提供了充分的实证证据,表明我们的元学习模型发现最优任务序列的速度显著快于非元学习的基线模型。

英文摘要:

Task sequencing (TS) is one of the core open problems in Deep Learning, arising in a plethora of real-world domains, from robotic assembly lines to autonomous driving. Unfortunately, prior work has not convincingly demonstrated the generalization ability of meta-learned TS methods to solve new TS problems, given few initial demonstrations. In this paper, we demonstrate that deep neural networks can meta-learn over an infinite prior of synthetically generated TS problems and achieve a few-shot generalization. We meta-learn a transformer-based architecture over datasets of sequencing trajectories generated from a prior distribution that samples sequencing problems as paths in directed graphs. In a large-scale experiment, we provide ample empirical evidence that our meta-learned models discover optimal task sequences significantly quicker than non-meta-learned baselines.

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。

↑