A deep latent space model for interpretable representation learning on directed graphs
文献类型：期刊论文
| 作者 | Yang, Hanxuan1,2; Kong, Qingchao1,2 ; Mao, Wenji1,2
|
| 刊名 | NEUROCOMPUTING
 |
| 出版日期 | 2024-04-01 |
| 卷号 | 576页码:13 |
| 关键词 | Graph representation learning Deep latent space model Model interpretability Variational auto-encoder Directed graph |
| ISSN号 | 0925-2312 |
| DOI | 10.1016/j.neucom.2024.127342 |
| 通讯作者 | Kong, Qingchao(qingchao.kong@ia.ac.cn) |
| 英文摘要 | Graph representation learning is a fundamental research problem for modeling relational data and benefits a number of downstream applications. Traditional Bayesian-based random graph models, such as the stochastic blockmodels (SBMs) and latent space models (LSMs), have proved effective to learn interpretable representations. To leverage both the good interpretability of random graph models and the powerful representation learning ability of deep learning-based methods such as graph neural networks (GNNs), some research proposes deep generative methods by combining the SBMs and GNNs. However, these combined methods have not fully considered the statistical properties of graphs which limits the model interpretability and applicability on directed graphs. To address these limitations in existing research, in this paper, we propose a Deep Latent Space Model (DLSM) for interpretable representation learning on directed graphs, by combining the LSMs and GNNs via a novel "lattice VAE"architecture. The proposed model generates multiple latent variables as node representations to adapt to the structure of directed graphs and improve model interpretability. Extensive experiments on representative real -world datasets demonstrate that our model achieves the state -of -the -art performances on link prediction and community detection with good interpretability. |
| 资助项目 | Ministry of Science and Technology of China[2020AAA0108405] ; NSFC, China[72293575] ; NSFC, China[72293573] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001177271500001 |
| 出版者 | ELSEVIER |
| 资助机构 | Ministry of Science and Technology of China ; NSFC, China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/56939]  |
| 专题 | 舆论大数据科学与技术应用联合实验室 |
| 通讯作者 | Kong, Qingchao |
| 作者单位 | 1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Yang, Hanxuan,Kong, Qingchao,Mao, Wenji. A deep latent space model for interpretable representation learning on directed graphs[J]. NEUROCOMPUTING,2024,576:13. |
| APA | Yang, Hanxuan,Kong, Qingchao,&Mao, Wenji.(2024).A deep latent space model for interpretable representation learning on directed graphs.NEUROCOMPUTING,576,13. |
| MLA | Yang, Hanxuan,et al."A deep latent space model for interpretable representation learning on directed graphs".NEUROCOMPUTING 576(2024):13. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。