arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.05253cs.LGcs.AI
收藏

一种结合领域约束的可扩展弱监督学习技术

A Scalable Technique for Weak-Supervised Learning with Domain Constraints

Intuit AI Research(财捷人工智能研究院)

Sudhir Agarwal, Anu Sreepathy, Lalla Mouatadid

AI总结:

提出一种可扩展端到端弱监督流水线,利用符号领域知识作为约束学习神经网络对未标记数据进行分类,通过同时考虑多个训练示例重写约束以利用高效优化技术,在MNIST变体任务上展现出显著优于先前方法的可扩展性。

摘要:

我们提出了一种新颖的可扩展端到端流水线,该流水线将符号领域知识作为约束,以弱监督方式学习神经网络来对未标记数据进行分类。我们的方法特别适用于数据由适合聚类友好表示学习的不同组(类)组成,且通过同时考虑多个训练示例,领域约束可被重新表述以利用高效数学优化技术的场景。我们在MNIST图像分类问题的一个变体上评估了我们的方法,其中训练示例由图像序列和序列所表示数字的总和组成,并表明我们的方法在可扩展性上显著优于依赖为每个训练示例计算所有满足约束组合的先前方法。

英文摘要:

We propose a novel scalable end-to-end pipeline that uses symbolic domain knowledge as constraints for learning a neural network for classifying unlabeled data in a weak-supervised manner. Our approach is particularly well-suited for settings where the data consists of distinct groups (classes) that lends itself to clustering-friendly representation learning and the domain constraints can be reformulated for use of efficient mathematical optimization techniques by considering multiple training examples at once. We evaluate our approach on a variant of the MNIST image classification problem where a training example consists of image sequences and the sum of the numbers represented by the sequences, and show that our approach scales significantly better than previous approaches that rely on computing all constraint satisfying combinations for each training example.

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。

↑