Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Unsupervised Framework for Evaluating and Explaining Structural Node Embeddings of Graphs (2306.10770v1)

Published 19 Jun 2023 in cs.LG and cs.SI

Abstract: An embedding is a mapping from a set of nodes of a network into a real vector space. Embeddings can have various aims like capturing the underlying graph topology and structure, node-to-node relationship, or other relevant information about the graph, its subgraphs or nodes themselves. A practical challenge with using embeddings is that there are many available variants to choose from. Selecting a small set of most promising embeddings from the long list of possible options for a given task is challenging and often requires domain expertise. Embeddings can be categorized into two main types: classical embeddings and structural embeddings. Classical embeddings focus on learning both local and global proximity of nodes, while structural embeddings learn information specifically about the local structure of nodes' neighbourhood. For classical node embeddings there exists a framework which helps data scientists to identify (in an unsupervised way) a few embeddings that are worth further investigation. Unfortunately, no such framework exists for structural embeddings. In this paper we propose a framework for unsupervised ranking of structural graph embeddings. The proposed framework, apart from assigning an aggregate quality score for a structural embedding, additionally gives a data scientist insights into properties of this embedding. It produces information which predefined node features the embedding learns, how well it learns them, and which dimensions in the embedded space represent the predefined node features. Using this information the user gets a level of explainability to an otherwise complex black-box embedding algorithm.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (32)
  1. Machine learning in social networks: embedding nodes, edges, communities, and graphs. Springer Nature, 2020.
  2. Learning role-based graph embeddings. arXiv preprint arXiv:1802.02896, 2018.
  3. Graph based anomaly detection and description: a survey. Data mining and knowledge discovery, 29(3):626–688, 2015.
  4. Gephi: An open source software for exploring and manipulating networks, 2009.
  5. Machine learning on graphs: A model and comprehensive taxonomy. arXiv preprint arXiv:2005.03675, page 1, 2020.
  6. Node structural representation learning using local signature matrix embedding [lsme]. 2022 (work in progress).
  7. Unsupervised framework for evaluating structural node embeddings of graphs. In Algorithms and Models for the Web Graph: 18th International Workshop, WAW 2023, Toronto, Canada, May 23–26, 2023, Proceedings. Springer, 2023.
  8. Evaluating node embeddings of complex networks. Journal of Complex Networks, 10(4):cnac030, 2022.
  9. Learning structural node embeddings via diffusion wavelets. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pages 1320–1329, 2018.
  10. Unpacking burt’s constraint measure. Social Networks, 62:50–57, 2020.
  11. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining, pages 855–864, 2016.
  12. Representation learning on graphs: Methods and applications. arXiv preprint arXiv:1709.05584, 2017.
  13. A survey of link prediction in social networks. In Social network data analytics, pages 243–275. Springer, 2011.
  14. Rolx: structural role extraction & mining in large graphs. In Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 1231–1239, 2012.
  15. Scalable and axiomatic ranking of network role similarity. ACM Trans. Knowl. Discov. Data, 8(1), feb 2014.
  16. A multi-purposed unsupervised framework for comparing embeddings of undirected and directed graphs. Network Science, 10(4):323–346, 2022.
  17. A scalable unsupervised framework for comparing graph embeddings. In International Workshop on Algorithms and Models for the Web-Graph, pages 52–67. Springer, 2020.
  18. An unsupervised framework for comparing graph embeddings. Journal of Complex Networks, 8(5):cnz043, 2020.
  19. Mining Complex Networks. Chapman and Hall/CRC, 2021.
  20. Rev2: Fraudulent user prediction in rating platforms. In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, pages 333–341. ACM, 2018.
  21. Edge weight prediction in weighted signed networks. In Data Mining (ICDM), 2016 IEEE 16th International Conference on, pages 221–230. IEEE, 2016.
  22. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781, 2013.
  23. Iterative classification in relational data. In Proc. AAAI-2000 workshop on learning statistical models from relational data, pages 13–20, 2000.
  24. Community detection supported by node embeddings (searching for a suitable method). In Complex Networks and Their Applications XI: Proceedings of The Eleventh International Conference on Complex Networks and their Applications: COMPLEX NETWORKS 2022—Volume 2, pages 221–232. Springer, 2023.
  25. Deepwalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 701–710, 2014.
  26. struc2vec: Learning node representations from structural identity. In Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, pages 385–394, 2017.
  27. Role discovery in networks. IEEE Transactions on Knowledge and Data Engineering, 27(4):1112–1131, 2015.
  28. A structural graph representation learning framework. WSDM ’20, page 483–491, New York, NY, USA, 2020. Association for Computing Machinery.
  29. On proximity and structural role-based embeddings in networks: Misconceptions, techniques, and applications. ACM Trans. Knowl. Discov. Data, 14(5), aug 2020.
  30. Twitch gamers: a dataset for evaluating proximity preserving and structural role-based node embeddings, 2021.
  31. Classic graph structural features outperform factorization-based graph embedding methods on community labeling. In Proceedings of the 2022 SIAM International Conference on Data Mining (SDM), pages 388–396. SIAM, 2022.
  32. Structural deep network embedding. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16, page 1225–1234, New York, NY, USA, 2016. Association for Computing Machinery.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (7)
  1. Ashkan Dehghan (3 papers)
  2. Kinga Siuta (1 paper)
  3. Agata Skorupka (1 paper)
  4. Andrei Betlen (1 paper)
  5. David Miller (22 papers)
  6. Bogumil Kaminski (10 papers)
  7. Pawel Pralat (63 papers)
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now