arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.01922cs.LGcs.AI
收藏

一种从弱监督中学习的通用框架

A General Framework for Learning from Weak Supervision

Carnegie Mellon University(卡内基梅隆大学);Microsoft Research(微软研究院);William & Mary(威廉玛丽学院);Singapore University of Technology and Design(新加坡科技设计大学);Peking University(北京大学);RIKEN AIP(理化学研究所人工智能项目);The University of Tokyo(东京大学);Mohamed bin Zayed University of AI(穆罕默德·本·扎耶德人工智能大学)

Hao Chen, Jindong Wang, Lei Feng, Xiang Li, Yidong Wang, Xing Xie, Masashi Sugiyama, Rita Singh, Bhiksha Raj

AI总结:

本文提出从弱监督中学习的通用框架GLWS,通过EM公式和NFA前向-后向算法将时间复杂度降至线性,在11个场景中表现优异。

摘要:

弱监督学习通常在适用性(难以适应具有多样弱监督的各种场景)和可扩展性(由于现有算法的复杂性)方面面临挑战,从而阻碍了其实际部署。本文提出了一种从弱监督中学习的通用框架(GLWS),并附带一种新颖的算法。GLWS的核心是一个期望最大化(EM)公式,它巧妙地适应了各种弱监督源,包括实例部分标签、聚合统计、成对观测和未标记数据。我们进一步提出了一种高级算法,该算法使用非确定性有限自动机(NFA)和前向-后向算法显著简化了EM的计算需求,有效地将现有解决方案中通常需要的二次或阶乘时间复杂度降低到线性规模。因此,从任意弱监督中学习的问题被转换为它们的NFA建模。GLWS不仅增强了机器学习模型的可扩展性,而且在11个弱监督场景中展示了卓越的性能和多功能性。我们希望我们的工作为该领域的进一步发展和实际部署铺平道路。

英文摘要:

Weakly supervised learning generally faces challenges in applicability to various scenarios with diverse weak supervision and in scalability due to the complexity of existing algorithms, thereby hindering the practical deployment. This paper introduces a general framework for learning from weak supervision (GLWS) with a novel algorithm. Central to GLWS is an Expectation-Maximization (EM) formulation, adeptly accommodating various weak supervision sources, including instance partial labels, aggregate statistics, pairwise observations, and unlabeled data. We further present an advanced algorithm that significantly simplifies the EM computational demands using a Non-deterministic Finite Automaton (NFA) along with a forward-backward algorithm, which effectively reduces time complexity from quadratic or factorial often required in existing solutions to linear scale. The problem of learning from arbitrary weak supervision is therefore converted to the NFA modeling of them. GLWS not only enhances the scalability of machine learning models but also demonstrates superior performance and versatility across 11 weak supervision scenarios. We hope our work paves the way for further advancements and practical deployment in this field.

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。

↑