Composition of Heterogeneous Node Embeddings - Unlocking the Power of Heterogeneous Graph Representation

• Silvio Fernando Angonese Universidade Federal do Rio Grande do Sul (UFRGS) http://orcid.org/0009-0001-6441-4320
• Renata Galante Universidade Federal do Rio Grande do Sul (UFRGS)

DOI: https://doi.org/10.5753/sbbd.2024.243436

Resumo

Heterogeneous graphs have high representation power, which can be maximized through node embeddings. Important embedding approaches are based on node features and node metapaths, applied individually. This paper proposes the creation of heterogeneous composition node embeddings, which are based on local node features, features from node neighbors, and node metapaths. This results in two types of composition embeddings: Features + Metapaths and Aggregated + Metapaths. Experiments have demonstrated superior performance compared to the baseline. In the experiments, our composition Aggregated Features + Metapaths embedding achieved a Micro-F1 score of 65.89% compared to 61.53% from the baseline, highlighting its effectiveness. Additionally, this paper also evaluates alternative models with these embedding compositions that outperform the state-of-the-art approach.

Palavras-chave: Heterogeneous Graph, Heterogeneous Embeddings, Composition Embeddings, Recommender Systems

Referências

Angonese, S. F. and Galante, R. (2024). AGHE: Approach for Generating Enhanced Heterogeneous Embeddings from Heterogeneous Graphs. In 51º Seminário Integrado de Software e Hardware (SEMISH), Brasilia, DF, Brazil.

Dong, Y., Chawla, N. V., and Swami, A. (2017). MetaPath2Vec: Scalable Representation Learning for Heterogeneous Networks. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’17, page 135–144, New York, NY, USA. Association for Computing Machinery.

Fu, X., Zhang, J., Meng, Z., and King, I. (2020). MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding. In Proceedings of The Web Conference 2020, WWW ’20, page 2331–2341, New York, NY, USA.

Hamilton, W. L., Ying, R., and Leskovec, J. (2017). Inductive Representation Learning on Large Graphs. In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17, page 1025–1035, Red Hook, NY, USA. Curran Associates Inc.

Jin, D., Huo, C., Liang, C., and Yang, L. (2021). Heterogeneous Graph Neural Network via Attribute Completion. In Proceedings of the Web Conference 2021, WWW ’21, page 391–400, New York, NY, USA. Association for Computing Machinery.

Mohd Razali, N. and Yap, B. (2011). Power comparisons of shapiro-wilk, kolmogorov-smirnov, lilliefors and anderson-darling tests. J. Stat. Model. Analytics, 2.

Santana, D. and Ribeiro, L. (2023). Approximate similarity joins over dense vector embeddings. In Anais do XXXVIII Simpósio Brasileiro de Bancos de Dados, pages 51–62, Porto Alegre, RS, Brasil. SBC.

Sun, Y. and Han, J. (2012). Mining Heterogeneous Information Networks: Principles and Methodologies. Morgan amp; Claypool Publishers.

Sun, Y., Han, J., Yan, X., Yu, P. S., and Wu, T. (2020). PathSim: Meta Path-Based Top-K Similarity Search in Heterogeneous Information Networks. Proc. VLDB Endow., 4(11):992–1003.

Wang, X., Bo, D., Shi, C., Fan, S., Ye, Y., and Yu, P. S. (2023). A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources. IEEE Transactions on Big Data, 9(2):415–436.

Wu, S., Sun, F., Zhang, W., Xie, X., and Cui, B. (2022). Graph Neural Networks in Recommender Systems: A Survey. ACM Comput. Surv., 55(5).

Ying, R., He, R., Chen, K., Eksombatchai, P., Hamilton, W. L., and Leskovec, J. (2018). Graph Convolutional Neural Networks for Web-Scale Recommender Systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery amp; Data Mining, KDD ’18, page 974–983, New York, NY, USA. Association for Computing Machinery.

Zhang, C., Song, D., Huang, C., Swami, A., and Chawla, N. V. (2019). Heterogeneous Graph Neural Network. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery amp; Data Mining, KDD ’19, page 793–803, New York, NY, USA. Association for Computing Machinery.