EUVIMEDEUVIMED entdecken
Crossref

Time-Aware Dynamic Graph Embedding for Asynchronous Structural Evolution

Yu Yang, Hongzhi Yin, Jiannong Cao, Tong Chen, Quoc Viet Hung Nguyen, Xiaofang Zhou, Lei Chen

IEEE Transactions on Knowledge and Data Engineering · 01.09.2023 · 35 (9) · 9656-9670

DOI: 10.1109/tkde.2023.3246059 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, erschienen am 01.09.2023. Verfasst von Yu Yang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: Shenzhen-Hong Kong-Macau Technology Research Programme Type C, Hong Kong Research Grants Council, Theme-based Research Scheme.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dynamic graphs refer to graphs whose structure dynamically changes over time. Despite the benefits of learning vertex representations (i.e., embeddings) for dynamic graphs, existing works merely view a dynamic graph as a sequence of changes within the vertex connections, neglecting the crucial asynchronous nature of such dynamics where the evolution of each local structure starts at different times and lasts for various durations. To maintain asynchronous structural evolutions within the graph, we innovatively formulate dynamic graphs as temporal edge sequences associated with joining time of vertices (ToV) and timespan of edges (ToE). Then, a time-aware Transformer is proposed to embed vertices’ dynamic connections and ToEs into the learned vertex representations. Meanwhile, we treat each edge sequence as a whole and embed its ToV of the first vertex to further encode the time-sensitive information. Extensive evaluations on several datasets show that our approach outperforms the state-of-the-art in a wide range of graph mining tasks. At the same time, it is very efficient and scalable for embedding large-scale dynamic graphs.

Förderung

  • Shenzhen-Hong Kong-Macau Technology Research Programme Type C
  • Hong Kong Research Grants Council
  • Theme-based Research Scheme
  • Research Impact Fund
  • Collaborative Research Fund
  • General Research Fund
  • National Natural Science Foundation of China
  • PolyU Research and Innovation Office

Zitieren

APA

Yang, Y., Yin, H., Cao, J., Chen, T., Nguyen, Q. V. H., Zhou, X., & Chen, L. (2023). Time-Aware Dynamic Graph Embedding for Asynchronous Structural Evolution. IEEE Transactions on Knowledge and Data Engineering, 35(9), 9656-9670. https://doi.org/10.1109/tkde.2023.3246059

Vancouver

Yang Y, Yin H, Cao J, Chen T, Nguyen QVH, Zhou X, et al. Time-Aware Dynamic Graph Embedding for Asynchronous Structural Evolution. IEEE Transactions on Knowledge and Data Engineering. 2023;35(9):9656-9670. doi:10.1109/tkde.2023.3246059

BibTeX
@article{Yang2023,
  author = {Yang, Yu and Yin, Hongzhi and Cao, Jiannong and Chen, Tong and Nguyen, Quoc Viet Hung and Zhou, Xiaofang and Chen, Lei},
  title = {Time-Aware Dynamic Graph Embedding for Asynchronous Structural Evolution},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year = {2023},
  volume = {35},
  number = {9},
  pages = {9656--9670},
  doi = {10.1109/tkde.2023.3246059}
}
Kostenlos starten →