Abstract
In the field of node representation learning the task of interpreting latent dimensions has become a prominent, well-studied research topic. The contribution of this work focuses on appraising the interpretability of another rarely-exploited feature of node embeddings increasingly utilised in recommendation and consumption diversity studies: inter-node embedded distances. Introducing a new method to measure how understandable the distances between nodes are, our work assesses how well the proximity weights derived from a network before embedding relate to the node closeness measurements after embedding. Testing several classical node embedding models, our findings reach a conclusion familiar to practitioners albeit rarely cited in literature—the matrix factorisation model SVD is the most interpretable through 1, 2 and even higher-order proximities.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Afchar, D., Hennequin, R., Guigue, V.: Of spiky SVDs and music recommendation. In: Proceeding of the 17th RecSys ACM Conference on Recommender Systems, pp. 926–932 (2023)
Anderson, A., Maystre, L., Anderson, I., Mehrotra, R., Lalmas, M.: Algorithmic effects on the diversity of consumption on spotify. In: Proceedings of The Web Conference 2020, pp. 2155–2165. WWW ’20, Association for Computing Machinery, New York, NY, USA (2020)
Barkan, O., Koenigstein, N.: Item2vec: neural item embedding for collaborative filtering (2016). arXiv:1603.04259
Caselles-Dupré, H., Lesaint, F., Royo-Letelier, J.: Word2vec applied to recommendation: hyperparameters matter. In: Proceedings of the 12th ACM Conference on Recommender Systems RecSys’18, pp. 352–356 (2018)
Dalmia, A., Gupta, M.: Towards interpretation of node embeddings. In: Companion Proceedings of the The Web Conference 2018, pp. 945–952 (2018)
Gogoglou, A., Bruss, C.B., Hines, K.E.: On the interpretability and evaluation of graph representation learning (2019). arXiv:1910.03081
Goyal, P., Ferrara, E.: Gem: a python package for graph embedding methods. J. Open Sour. Soft. 3(29), 876 (2018)
Goyal, P., Ferrara, E.: Graph embedding techniques, applications, and performance: a survey. Knowl.-Based Syst. 151, 78–94 (2018)
Grover, A., Leskovec, J.: Node2vec: scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 855–864. Association for Computing Machinery, New York, NY, USA (2016)
Han, H., Li, W., Wang, J., Qin, G., Qin, X.: Enhance explainability of manifold learning. Neurocomputing 500, 877–895 (2022)
Jin, J., Heimann, M., Jin, D., Koutra, D.: Towards understanding and evaluating structural node embeddings (2021)
Lapesa, G., Evert, S., Schulte im Walde, S.: Contrasting syntagmatic and paradigmatic relations: insights from distributional semantic models. In: Proceedings of the Third Joint Conference on Lexical and Computational Semantics (*SEM 2014), pp. 160–170. Association for Computational Linguistics and Dublin City University, Dublin, Ireland (2014)
Liu, N., Huang, X., Li, J., Hu, X.: On interpretation of network embedding via taxonomy induction. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1812–1820 (2018)
Lorrain, F., White, H.C.: Structural equivalence of individuals in social networks. J. Math. Sociol. 1(1), 49–80 (1971)
McFee, B., Lanckriet, G.R.: The natural language of playlists. In: ISMIR, vol. 11, pp. 537–541 (2011)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: Bengio, Y., LeCun, Y. (eds.) 1st International Conference on Learning Representations, ICLR 2013, Scottsdale, Ariz., USA, May 2–4 (2013)
Musto, C., Semeraro, G., Degemmis, M., Lops, P.: Word embedding techniques for content-based recommender systems: an empirical evaluation. In: RecSys Posters, vol. 1441 (2015)
Ozsoy, M.G.: From word embeddings to item recommendation (2016). arXiv:1601.01356
Papreja, P., Venkateswara, H., Panchanathan, S.: Representation, exploration and recommendation of playlists. In: Cellier, P., Driessens, K. (eds.) Machine Learning and Knowledge Discovery in Databases - International Workshops of ECML PKDD 2019, pp. 543–550. Springer, Switzerland (2020)
Park, H.: Providing post-hoc explanation for node representation learning models through inductive conformal predictions. IEEE Access 11, 1202–1212 (2022)
Perozzi, B., Al-Rfou, R., Skiena, S.: Deepwalk: Online learning of social representations. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge discovery and data mining, pp. 701–710 (2014)
Piaggesi, S., Khosla, M., Panisson, A., Anand, A.: Dine: dimensional interpretability of node embeddings (2023). arXiv:2310.01162
Rossi, R.A., Ahmed, N.K.: Role discovery in networks. IEEE Trans. Knowl. Data Eng. 27(4), 1112–1131 (2015)
Sahlgren, M.: The Word-Space Model: using distributional analysis to represent syntagmatic and paradigmatic relations between words in high-dimensional vector spaces. Ph.D. thesis, Institutionen för lingvistik (2006)
Schlechtweg, D., Oguz, C., Schulte im Walde, S.: Second-order co-occurrence sensitivity of skip-gram with negative sampling. In: Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pp. 24–30. Association for Computational Linguistics, Florence, Italy (2019)
Scholkemper, M., Schaub, M.T.: Local, global and scale-dependent node roles. In: 2021 IEEE International Conference on Autonomous Systems (ICAS), pp. 1–5 (2021)
Villermet, Q., Poiroux, J., Moussallam, M., Louail, T., Roth, C.: Follow the guides: disentangling human and algorithmic curation in online music consumption. In: Proceedings of the 15th ACM Conference on Recommender Systems, pp. 380–389 (2021)
Waller, I., Anderson, A.: Generalists and specialists: Using community embeddings to quantify activity diversity in online platforms. In: Proceedings of The Web Conference 2019, pp. 1954–1964. WWW ’19, Association for Computing Machinery, New York, NY, USA (2019)
Wang, D., Cui, P., Zhu, W.: Structural deep network embedding. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1225–1234. Association for Computing Machinery, New York (2016)
Acknowledgements
This paper has been partially realized in the framework of the “RECORDS” grant (ANR-2019-CE38-0013) funded by the ANR (French National Agency of Research).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Disclosure of Interests.
There were no conflicts of interest relating to the production of this work.
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Shakespeare, D., Roth, C. (2024). Interpreting Node Embedding Distances Through n-Order Proximity Neighbourhoods. In: Botta, F., Macedo, M., Barbosa, H., Menezes, R. (eds) Complex Networks XV. CompleNet-Live 2024. Springer Proceedings in Complexity. Springer, Cham. https://doi.org/10.1007/978-3-031-57515-0_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-57515-0_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-57514-3
Online ISBN: 978-3-031-57515-0
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)