skip to main content
10.1145/3488560.3498428acmconferencesArticle/Chapter ViewAbstractPublication PageswsdmConference Proceedingsconference-collections
research-article
Public Access

On Generalizing Static Node Embedding to Dynamic Settings

Published: 15 February 2022 Publication History

Abstract

Temporal graph embedding has been widely studied thanks to its superiority in tasks such as prediction and recommendation. Despite the advances in algorithms and novel frameworks such as deep learning, there has been relatively little work on systematically studying the properties of temporal network models and their cornerstones, the graph time-series representations that are used in these approaches. This paper aims to fill this gap by introducing a general framework that extends an arbitrary existing static embedding approach to handle dynamic tasks, and conducting a systematic study of seven base static embedding methods and six temporal network models. Our framework generalizes static node embeddings derived from the time-series representation of stream data to the dynamic setting by modeling the temporal dependencies with classic models such as the reachability graph. While previous works on dynamic modeling and embedding have focused on representing a stream of timestamped edges using a time-series of graphs based on a specific time-scale (\eg, 1 month), we introduce the notion of an ε-graph time-series that uses a fixed number of edges for each graph, and show its superiority in practical settings over the standard solution. From the 42 methods that our framework subsumes, we find that leveraging the new ε-graph time-series representation and capturing temporal dependencies with the proposed reachability or summary graph tend to perform well. Furthermore, the new dynamic embedding methods based on our framework perform comparably and on average better than the state-of-the-art embedding methods designed specifically for temporal graphs in link prediction tasks.

Supplementary Material

MP4 File (WSDM22-fp323.mp4)
The presentation video for the paper, "On Generalizing Static Node Embedding to Dynamic Settings". Despite the recent increasing interest in temporal networks in the field of representation learning, there has been relatively little work that systematically studies the properties of temporal network models and their cornerstones, the graph time-series representations. This works attempts to fill this gap by proposing a general yet powerful framework. Our proposed framework gives rise to new dynamic embedding methods by combining these graph time-series representations, temporal models, and base static embedding methods.

References

[1]
N. K. Ahmed, R. A. Rossi, R. Zhou, J. B. Lee, X. Kong, T. L. Willke, and H. Eldardiry. Learning role-based graph embeddings. In IJCAI StarAI, 2018.
[2]
A. Bojchevski and S. Günnemann. Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking. In ICLR, 2018.
[3]
S. Cao, W. Lu, and Q. Xu. Grarep: Learning graph representations with global structural information. In CIKM, pages 891--900. ACM, 2015.
[4]
K. G. Coffman and A. M. Odlyzko. Growth of the internet. In Optical fiber telecommunications IV-B, pages 17--56. Elsevier, 2002.
[5]
C. Donnat, M. Zitnik, D. Hallac, and J. Leskovec. Learning structural node embeddings via diffusion wavelets. In KDD, pages 1320--1329. ACM, 2018.
[6]
P. Goyal, S. R. Chhetri, and A. Canedo. dyngraph2vec: Capturing network dynamics using dynamic graph representation learning. Knowledge-Based Systems, page 104816, 2019.
[7]
P. Goyal, N. Kamra, X. He, and Y. Liu. Dyngem: Deep embedding method for dynamic graphs. arXiv preprint arXiv:1805.11273, 2018.
[8]
A. Grover and J. Leskovec. node2vec: Scalable feature learning for networks. In KDD, pages 855--864, 2016.
[9]
R. Hisano. Semi-supervised graph embedding approach to dynamic link prediction. In International Workshop on Complex Networks, pages 109--121. Springer, 2018.
[10]
D. Jin, M. Heimann, R. Rossi, and D. Koutra. node2bits: Compact time-and attribute-aware node representations for user stitching. In ECML PKDD, page 22, 2019.
[11]
D. Jin, R. A. Rossi, E. Koh, S. Kim, A. Rao, and D. Koutra. Latent network summarization: Bridging network embedding and summarization. In KDD. ACM, 2019.
[12]
J. Jin, M. Heimann, D. Jin, and D. Koutra. Toward understanding and evaluating structural node embeddings. ACM Trans. Knowl. Discov. Data, 16(3), nov 2021.
[13]
S. Kumar, X. Zhang, and J. Leskovec. Predicting dynamic embedding trajectory in temporal interaction networks. In KDD, pages 1269--1278. ACM, 2019.
[14]
J. Leskovec, J. Kleinberg, and C. Faloutsos. Graphs over time: Densification laws, shrinking diameters and possible explanations. In KDD, 2005.
[15]
J. Leskovec and A. Krevl. SNAP Datasets: Stanford large network dataset collection. http://snap.stanford.edu/data, June 2014.
[16]
J. Li, H. Dani, X. Hu, J. Tang, Y. Chang, and H. Liu. Attributed network embedding for learning in a dynamic environment. In CIKM, pages 387--396. ACM, 2017.
[17]
Y. Liu, T. Safavi, A. Dighe, and D. Koutra. Graph summarization methods and applications: A survey. ACM Computing Surveys (CSUR), 51(3):1--34, 2018.
[18]
G. H. Nguyen, J. B. Lee, R. A. Rossi, N. K. Ahmed, E. Koh, and S. Kim. Continuous-time dynamic network embeddings. In WWW BigNet, 2018.
[19]
A. Pareja, G. Domeniconi, J. Chen, T. Ma, T. Suzumura, H. Kanezashi, T. Kaler, T. Schardl, and C. Leiserson. Evolvegcn: Evolving graph convolutional networks for dynamic graphs. In AAAI, volume 34, pages 5363--5370, 2020.
[20]
L. F. Ribeiro, P. H. Saverese, and D. R. Figueiredo. Struc2vec: Learning node representations from structural identity. In KDD, 2017.
[21]
R. A. Rossi and N. K. Ahmed. The network data repository with interactive graph analytics and visualization. In AAAI, 2015.
[22]
R. A. Rossi, N. K. Ahmed, H. Eldardiry, and R. Zhou. Similarity-based multi-label learning. In IJCNN, pages 1--8, 2018.
[23]
R. A. Rossi, D. Jin, S. Kim, N. K. Ahmed, D. Koutra, and J. B. Lee. On proximity and structural role-based embeddings in networks: Misconceptions, techniques, and applications. ACM TKDD, 14(5):1--37, 2020.
[24]
R. A. Rossi and J. Neville. Time-evolving relational classification and ensemble methods. In PAKDD, volume 7301, pages 1--13. Springer, 2012.
[25]
A. Sankar, Y. Wu, L. Gou, W. Zhang, and H. Yang. Dysat: Deep neural representation learning on dynamic graphs via self-attention networks. In WSDM, pages 519--527, 2020.
[26]
U. Singer, I. Guy, and K. Radinsky. Node embedding over temporal graphs. In IJCAI, pages 4605--4612, 7 2019.
[27]
S. Soundarajan, A. Tamersoy, E. B. Khalil, T. Eliassi-Rad, D. H. Chau, B. Gallagher, and K. A. Roundy. Generating graph snapshots from streaming edge data. In WWW Companion Volume, pages 109--110. ACM, 2016.
[28]
J. Tang, M. Qu, M. Wang, M. Zhang, J. Yan, and Q. Mei. LINE: Large-scale Information Network Embedding. In WWW, pages 1067--1077, 2015.
[29]
H. Xue, L. Yang, W. Jiang, Y. Wei, Y. Hu, and Y. Lin. Modeling dynamic heterogeneous network forlink prediction using hierarchical attentionwith temporal rnn. In ECML PKDD, 2020.
[30]
Z. Zhang, P. Cui, J. Pei, X. Wang, and W. Zhu. Timers: Error-bounded svd restart on dynamic networks. In AAAI, 2018.
[31]
L. Zhou, Y. Yang, X. Ren, F. Wu, and Y. Zhuang. Dynamic network embedding by modeling triadic closure process. In AAAI, 2018.
[32]
J. Zhu, X. Lu, M. Heimann, and D. Koutra. Node proximity is all you need: Unified structural and positional node and graph embedding. In SDM, pages 163--171. SIAM, 2021.
[33]
Y. Zuo, G. Liu, H. Lin, J. Guo, X. Hu, and J. Wu. Embedding temporal network via neighborhood formation. In KDD, pages 2857--2866, 2018.

Cited By

View all
  • (2023)From random-walks to graph-sprints: a low-latency node embedding framework on continuous-time dynamic graphsProceedings of the Fourth ACM International Conference on AI in Finance10.1145/3604237.3626842(176-184)Online publication date: 27-Nov-2023
  • (2022)DHGEEP: A Dynamic Heterogeneous Graph-Embedding Method for Evolutionary PredictionMathematics10.3390/math1022419310:22(4193)Online publication date: 9-Nov-2022

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
WSDM '22: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining
February 2022
1690 pages
ISBN:9781450391320
DOI:10.1145/3488560
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 15 February 2022

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. dynamic networks
  2. graph time-series
  3. representation learning

Qualifiers

  • Research-article

Funding Sources

Conference

WSDM '22

Acceptance Rates

Overall Acceptance Rate 498 of 2,863 submissions, 17%

Upcoming Conference

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)136
  • Downloads (Last 6 weeks)29
Reflects downloads up to 13 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2023)From random-walks to graph-sprints: a low-latency node embedding framework on continuous-time dynamic graphsProceedings of the Fourth ACM International Conference on AI in Finance10.1145/3604237.3626842(176-184)Online publication date: 27-Nov-2023
  • (2022)DHGEEP: A Dynamic Heterogeneous Graph-Embedding Method for Evolutionary PredictionMathematics10.3390/math1022419310:22(4193)Online publication date: 9-Nov-2022

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Login options

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media