发表状态 | 已发表Published |
题名 | Streaming Graph Embeddings via Incremental Neighborhood Sketching |
作者 | |
发表日期 | 2022 |
发表期刊 | IEEE Transactions on Knowledge and Data Engineering
![]() |
ISSN/eISSN | 1041-4347 |
摘要 | Graph embeddings have become a key paradigm to learn node representations and facilitate downstream graph analysis tasks. Many real-world scenarios such as online social networks and communication networks involve streaming graphs, where edges connecting nodes are continuously received in a streaming manner, making the underlying graph structures evolve over time. Such a streaming graph raises great challenges for graph embedding techniques not only in capturing the structural dynamics of the graph, but also in efficiently accommodating high-speed edge streams. Against this background, we propose SGSketch, a highly-efficient streaming graph embedding technique via incremental neighborhood sketching. SGSketch cannot only generate high-quality node embeddings from a streaming graph by gradually forgetting outdated streaming edges, but also efficiently update the generated node embeddings via an incremental embedding updating mechanism. Our extensive evaluation compares SGSketch against a sizable collection of state-of-the-art techniques using both synthetic and real-world streaming graphs. The results show that SGSketch achieves superior performance on different graph analysis tasks, showing 31.9% and 21.9% improvement on average over the best-performing static and dynamic graph embedding baselines, respectively. Moreover, SGSketch is significantly more efficient in both embedding learning and incremental embedding updating processes, showing 54x-1813x and 118x-1955x speedup over the baseline techniques, respectively. |
关键词 | Dynamic graph embedding Streaming graph Concept drift Data sketching Consistent weighted sampling |
DOI | 10.1109/TKDE.2022.3149999 |
URL | 查看来源 |
收录类别 | SCIE |
语种 | 英语English |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Information Systems ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000964880800065 |
Scopus入藏号 | 2-s2.0-85124742718 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | https://repository.uic.edu.cn/handle/39GCC9TT/8951 |
专题 | 理工科技学院 |
作者单位 | 1.Department of Computer and Information Science, University of Macau, 59193 Taipa, Macau, China 2.Division of Science and Technology, BNU-HKBU United International College, 125809 Zhuhai, Guangdong, China 3.Department of Software Technology, Technische Universiteit Delft, 2860 Delft, South Holland, Netherlands, 2628 CD 4.Department of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, China 5.Department of informatics, U. of Fribourg, Fribourg, Switzerland |
推荐引用方式 GB/T 7714 | Yang, Dingqi,Qu, Bingqing,Yang, Jieet al. Streaming Graph Embeddings via Incremental Neighborhood Sketching[J]. IEEE Transactions on Knowledge and Data Engineering, 2022. |
APA | Yang, Dingqi, Qu, Bingqing, Yang, Jie, Wang, Liang, & Cudre-Mauroux, Philipe. (2022). Streaming Graph Embeddings via Incremental Neighborhood Sketching. IEEE Transactions on Knowledge and Data Engineering. |
MLA | Yang, Dingqi,et al."Streaming Graph Embeddings via Incremental Neighborhood Sketching". IEEE Transactions on Knowledge and Data Engineering (2022). |
条目包含的文件 | 条目无相关文件。 |
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