Zero-Shot and Few-Shot Learning With Knowledge Graphs: A Comprehensive Survey
Zero-Shot and Few-Shot Learning With Knowledge Graphs: A Comprehensive Survey
复制标题
DOI：
10.1109/jproc.2023.3279374
复制
发表时间：
2021-12
影响因子：
20.6
通讯作者：
Jiaoyan Chen;Yuxia Geng;Zhuo Chen;Jeff Z. Pan;Yuan He;Wen Zhang;Ian Horrocks;Hua-zeng Chen
中科院分区：
文献类型：
--
作者：
Jiaoyan Chen;Yuxia Geng;Zhuo Chen;Jeff Z. Pan;Yuan He;Wen Zhang;Ian Horrocks;Hua-zeng Chen
机器学习（ML），特别是深度神经网络，已经取得了巨大的成功，但其中许多通常依赖于大量标记样本进行监督。由于实际应用中不断出现的预测目标和昂贵的样本标注，并不总是准备好足够的标记训练数据，因此样本短缺的ML正在被广泛研究。在所有这些研究中，许多研究倾向于利用辅助信息，包括知识图（KG）形式的信息，以减少对标记样本的依赖。在本次调查中，我们全面回顾了90多篇关于KG-aware研究的文章，主要针对两种主要的样本短缺设置：零次学习（zero-shot learning， ZSL），其中一些待预测的类没有标记样本；少次学习（few-shot learning， FSL），其中一些待预测的类只有少量可用的标记样本。本文首先介绍了ZSL和FSL中使用的KGs及其构建方法，然后对基于KGs的ZSL和FSL方法进行了系统的分类和总结，并将其分为基于映射的、基于数据增强的、基于传播的和基于优化的几种不同的范式。接下来，我们介绍了不同的应用，不仅包括图像分类、问题回答、文本分类和知识提取等KG增强预测任务，还包括KG完成任务和每个任务的一些典型评价资源。我们最终会从不同的角度讨论一些挑战和开放性问题。
Machine learning (ML), especially deep neural networks, has achieved great success, but many of them often rely on a number of labeled samples for supervision. As sufficient labeled training data are not always ready due to, e.g., continuously emerging prediction targets and costly sample annotation in real-world applications, ML with sample shortage is now being widely investigated. Among all these studies, many prefer to utilize auxiliary information including those in the form of knowledge graph (KG) to reduce the reliance on labeled samples. In this survey, we have comprehensively reviewed over 90 articles about KG-aware research for two major sample shortage settings—zero-shot learning (ZSL) where some classes to be predicted have no labeled samples and few-shot learning (FSL) where some classes to be predicted have only a small number of labeled samples that are available. We first introduce KGs used in ZSL and FSL as well as their construction methods and then systematically categorize and summarize KG-aware ZSL and FSL methods, dividing them into different paradigms, such as the mapping-based, the data augmentation, the propagation-based, and the optimization-based. We next present different applications, including not only KG augmented prediction tasks such as image classification, question answering, text classification, and knowledge extraction but also KG completion tasks and some typical evaluation resources for each task. We eventually discuss some challenges and open problems from different perspectives.