arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.00660cs.LGcs.AI
收藏

受人类同伴学习启发的资源受限知识扩散过程

Resource-constrained knowledge diffusion processes inspired by human peer learning

Ying Wu College of Computing(伍莹计算机学院);New Jersey Institute of Technology(新泽西理工学院)

Ehsan Beikihassan, Amy K. Hoover, Ioannis Koutis, Ali Parviz, Niloofar Aghaieabiane

AI总结:

本文研究资源受限下人工学习者网络中的知识扩散过程,受人类同伴学习启发,通过协调者组建学习小组,实验证明该方法能有效利用资源并设计出抗噪声标签过拟合的模块化神经模型。

摘要:

我们考虑一个给定人工学习者群体的场景,目标是在训练资源受限的条件下优化性能的聚合度量。该问题源于对人类教育系统中同伴学习的研究。在此背景下,我们研究交互人工学习者网络中自然的知识扩散过程。所谓“自然”,是指反映人类同伴学习的过程,其中学生的内部状态和学习过程大多不透明,主要的自由度在于协调者对同伴学习小组的组建,该协调者可以在将学习者分配到同伴小组之前对其进行评估。此外,我们通过实验证明,这类过程确实能有效利用训练资源,并支持模块化神经模型的设计,使其具备泛化能力,同时不易过拟合噪声标签。

英文摘要:

We consider a setting where a population of artificial learners is given, and the objective is to optimize aggregate measures of performance, under constraints on training resources. The problem is motivated by the study of peer learning in human educational systems. In this context, we study natural knowledge diffusion processes in networks of interacting artificial learners. By `natural', we mean processes that reflect human peer learning where the students' internal state and learning process is mostly opaque, and the main degree of freedom lies in the formation of peer learning groups by a coordinator who can potentially evaluate the learners before assigning them to peer groups. Among else, we empirically show that such processes indeed make effective use of the training resources, and enable the design of modular neural models that have the capacity to generalize without being prone to overfitting noisy labels.

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。

↑