Abstract
Graph node embedding learning has gained significant attention with the advancement of graph neural networks (GNNs). The essential purpose of graph node embedding is down-scaling high-dimensional graph features to a lower-dimensional space while maximizing the retention of original structural information. This paper focuses on selecting the appropriate graph node embedding dimension for hidden layers, ensuring the effective representation of node information and preventing overfitting. We propose an algorithm based on the entropy minimization principle, called Minimum Overall Entropy (MOE), which combines graph node structural information and attribute information. We refer to one-dimensional and multi-dimensional structural entropy (MDSE) as a graph’s structural entropy. A novel algorithm combines graph Shannon entropy, MDSE, and prior knowledge for faster convergence of optimal MDSE. We introduce an inner product-based metric, attribute entropy, to quantify node characteristics and simplify its calculation. Extensive experiments on Cora, Citeseer, and Pubmed datasets reveal that MOE, requiring just one computation round, surpasses baseline GNNs.
Supported by the National Key R&D Program of China (No. 2022YFF0503900) and Key R &D Program of Shandong Province (No. 2021CXGC010104).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bianconi, G., Pin, P., Marsili, M.: Assessing the relevance of node features for network structure. Proc. Natl. Acad. Sci. 106(28), 11433–11438 (2009)
Bonchev, D., Trinajstić, N.: Information theory, distance matrix, and molecular branching. J. Chem. Phys. 67(10), 4517–4533 (1977)
Brooks, F.P., Jr.: Three great challenges for half-century-old computer science. J. ACM (JACM) 50(1), 25–26 (2003)
Chen, M., Wei, Z., Huang, Z., Ding, B., Li, Y.: Simple and deep graph convolutional networks. In: International Conference on Machine Learning, pp. 1725–1735. PMLR (2020)
Choi, Y., Szpankowski, W.: Compression of graphical structures: fundamental limits, algorithms, and experiments. IEEE Trans. Inf. Theory 58(2), 620–638 (2012)
Fang, P., et al.: How to realize efficient and scalable graph embeddings via an entropy-driven mechanism. IEEE Trans. Big Data 9(1), 358–371 (2022)
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 (2016)
Hamilton, W.L., Ying, R., Leskovec, J.: Inductive representation learning on large graphs. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 1025–1035 (2017)
Hamilton, W.L., Ying, R., Leskovec, J.: Representation learning on graphs: methods and applications. In: Proceedings of the IEEE Data Engineering Bulletin, September 2017 (2017). http://sites.computer.org/debull/A17sept/p52.pdf
Huang, X., Song, Q., Li, Y., Hu, X.: Graph recurrent networks with attributed random walks. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 732–740 (2019)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24–26 April 2017, Conference Track Proceedings. OpenReview.net (2017). https://openreview.net/forum?id=SJU4ayYgl
Li, A., Pan, Y.: Structural information and dynamical complexity of networks. IEEE Trans. Inf. Theor. 62(6), 3290–3339 (2016)
Li, C., Jia, K., Shen, D., Shi, C.J.R., Yang, H.: Hierarchical representation learning for bipartite graphs. In: IJCAI, vol. 19, pp. 2873–2879 (2019)
Liu, Z., Shi, K., Zhang, K., Ou, W., Wang, L.: Discriminative sparse embedding based on adaptive graph for dimension reduction. Eng. Appl. Artif. Intell. 94, 103758 (2020)
Luo, G., et al.: Dynamically constructed network with error correction for accurate ventricle volume estimation. Med. Image Anal. 64, 101723 (2020)
Luo, G., et al.: Graph entropy guided node embedding dimension selection for graph neural networks. In: Zhou, Z.H. (ed.) Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, pp. 2767–2774. International Joint Conferences on Artificial Intelligence Organization, August 2021. https://doi.org/10.24963/ijcai.2021/381. Main Track
Ou, M., Cui, P., Pei, J., Zhang, Z., Zhu, W.: Asymmetric transitivity preserving graph embedding. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1105–1114 (2016)
Pan, S., Hu, R., Long, G., Jiang, J., Yao, L., Zhang, C.: Adversarially regularized graph autoencoder for graph embedding. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, pp. 2609–2615. International Joint Conferences on Artificial Intelligence Organization, July 2018. https://doi.org/10.24963/ijcai.2018/362
Peng, H., et al.: Hierarchical taxonomy-aware and attentional graph capsule RCNNs for large-scale multi-label text classification. IEEE Trans. Knowl. Data Eng. 33(6), 2505–2519 (2019)
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)
Rashevsky, N.: Life, information theory, and topology. Bull. Math. Biophys. 17(3), 229–235 (1955)
Raychaudhury, C., Ray, S., Ghosh, J., Roy, A., Basak, S.: Discrimination of isomeric structures using information theoretic topological indices. J. Comput. Chem. 5(6), 581–588 (1984)
Rosvall, M., Bergstrom, C.T.: Maps of random walks on complex networks reveal community structure. Proc. Natl. Acad. Sci. 105(4), 1118–1123 (2008)
Schubert, E., Sander, J., Ester, M., Kriegel, H., Xu, X.: DBSCAN revisited, revisited: why and how you should (still) use DBSCAN. ACM Trans. Database Syst. 42(3), 19:1–19:21 (2017). https://doi.org/10.1145/3068335
Sculley, D.: Web-scale k-means clustering. In: Rappa, M., Jones, P., Freire, J., Chakrabarti, S. (eds.) Proceedings of the 19th International Conference on World Wide Web, WWW 2010, Raleigh, North Carolina, USA, 26–30 April 2010, pp. 1177–1178. ACM (2010). https://doi.org/10.1145/1772690.1772862
Sen, P., Namata, G., Bilgic, M., Getoor, L., Galligher, B., Eliassi-Rad, T.: Collective classification in network data. AI Mag. 29(3), 93 (2008)
Seshadhri, C., Sharma, A., Stolman, A., Goel, A.: The impossibility of low-rank representations for triangle-rich complex networks. Proc. Natl. Acad. Sci. 117(11), 5631–5637 (2020)
Shannon, C.: The lattice theory of information. Trans. IRE Prof. Group Inf. Theor. 1(1), 105–107 (1953)
Shen, X.J., Liu, S.X., Bao, B.K., Pan, C.H., Zha, Z.J., Fan, J.: A generalized least-squares approach regularized with graph embedding for dimensionality reduction. Pattern Recogn. 98, 107023 (2020)
Sun, Q., et al.: Sugar: subgraph neural network with reinforcement pooling and self-supervised mutual information mechanism. In: Proceedings of the Web Conference 2021, pp. 2081–2091 (2021)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks (2018). https://iclr.cc/Conferences/2018/Schedule?showEvent=299
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., Philip, S.Y.: A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32(1), 4–24 (2020)
Xie, Y., Li, S., Yang, C., Wong, R.C.W., Han, J.: When do GNNs work: understanding and improving neighborhood aggregation. In: IJCAI, pp. 1303–1309 (2020)
Xiong, K., Nie, F., Han, J.: Linear manifold regularization with adaptive graph for semi-supervised dimensionality reduction. In: IJCAI, pp. 3147–3153 (2017)
Yan, S., Xu, D., Zhang, B., Zhang, H.J.: Graph embedding: a general framework for dimensionality reduction. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 2, pp. 830–837. IEEE (2005)
Yi, Y., Wang, J., Zhou, W., Fang, Y., Kong, J., Lu, Y.: Joint graph optimization and projection learning for dimensionality reduction. Pattern Recogn. 92, 258–273 (2019)
Yin, Z., Shen, Y.: On the dimensionality of word embedding. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31. Curran Associates, Inc. (2018). https://proceedings.neurips.cc/paper/2018/file/b534ba68236ba543ae44b22bd110a1d6-Paper.pdf
Zhu, S.C., Wu, Y.N., Mumford, D.: Minimax entropy principle and its application to texture modeling. Neural Comput. 9(8), 1627–1660 (1997). https://doi.org/10.1162/neco.1997.9.8.1627
Zhu, X., Lei, C., Yu, H., Li, Y., Gan, J., Zhang, S.: Robust graph dimensionality reduction. In: IJCAI, pp. 3257–3263 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, X., Ding, Z., Wu, Y., Yan, J., Jiang, S., Cui, Q. (2023). Optimal Node Embedding Dimension Selection Using Overall Entropy. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14262. Springer, Cham. https://doi.org/10.1007/978-3-031-44201-8_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-44201-8_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44200-1
Online ISBN: 978-3-031-44201-8
eBook Packages: Computer ScienceComputer Science (R0)