Knowledge Commons of Institute of Automation,CAS
Quantum Probability-inspired Graph Neural Network for Document Representation and Classification | |
Yan, Peng1,2; Li, Lingjing1,2,3; Jin, Miaotianzi3; Zeng, Daniel1,2,3 | |
发表期刊 | Neurocomputing |
ISSN | 0925-2312 |
2021-07-20 | |
卷号 | 445页码:276-286 |
产权排序 | 1 |
文章类型 | 期刊论文 |
摘要 | Recent studies have found that text can be represented in Hilbert space through a neural network driven by quantum probability, which provides a unified representation of texts with different granularities without losing the performance of downstream tasks. However, these quantum probability-inspired methods only focus on intra-document semantics and lack modeling global structural information. In this paper, we explore the potential of combining quantum probability with graph neural network, and propose a quantum probability-inspired graph neural network model to capture global structural information of interaction between documents for document representation and classification. We build a document interaction graph for a given corpus based on document word relation and frequency information, then learn a graph neural network driven by quantum probability on the defined graph. First, the proposed model represents each document node in the graph as a superposition state in a Hilbert space. Then the proposed model further computes density matrix representations for nodes to encode document interaction as mixed states. Finally, the model computes classification probability by performing quantum measurement on the mixed states. Experiments on four document classification benchmarks show that the proposed model outperforms a variety of classical neural network models and the previous quantum probability-inspired model with much smaller parameter size. Extended analyses also demonstrate the robustness of the proposed model with limited training data and its ability to learn semantically distinguishable document representation. |
关键词 | Natural language processing Document representation Document classification Graph neural network Quantum probability |
DOI | 10.1016/j.neucom.2021.02.060 |
收录类别 | SCI |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48724 |
专题 | 多模态人工智能系统全国重点实验室_互联网大数据与信息安全 |
通讯作者 | Li, Lingjing |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences 2.Institute of Automation, Chinese Academy of Sciences 3.Shenzhen Artificial Intelligence and Data Science Institute |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yan, Peng,Li, Lingjing,Jin, Miaotianzi,et al. Quantum Probability-inspired Graph Neural Network for Document Representation and Classification[J]. Neurocomputing,2021,445:276-286. |
APA | Yan, Peng,Li, Lingjing,Jin, Miaotianzi,&Zeng, Daniel.(2021).Quantum Probability-inspired Graph Neural Network for Document Representation and Classification.Neurocomputing,445,276-286. |
MLA | Yan, Peng,et al."Quantum Probability-inspired Graph Neural Network for Document Representation and Classification".Neurocomputing 445(2021):276-286. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
1-s2.0-S092523122100(1744KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论