Semantic-Enriched Heterogeneous Embeddings for Enhanced Node Classification
Resumo
Sistemas de Informação dependem cada vez mais de dados heterogêneos e multimodais, o que dificulta a construção de representações de nós informativas. Este trabalho propõe um processo para geração de embeddings heterogêneos enriquecidos semanticamente, integrando características locais, representações multimodais e metapaths orientados por ontologia. Experimentos em um grafo de Pessoas demonstram que composições de embeddings superam embeddings individuais, alcançando maiores valores de F1-macro e maior estabilidade. Os resultados indicam que a combinação de semântica multimodal com metapaths orientados por ontologia melhora a qualidade das representações e a generalização em ambientes heterogêneos.
Referências
Ali, S. J., Guizzardi, G., and Bork, D. (2023). Enabling representation learning in ontology-driven conceptual modeling using graph neural networks. In Advanced Information Systems Engineering – 35th International Conference, CAiSE 2023, Zaragoza, Spain, June 12–16, 2023, Proceedings, pages 278–294. Springer.
Angonese, S. and Galante, R. (2024a). AGHE – approach for generating enhanced heterogeneous embeddings from heterogeneous graphs. In Proceedings of the LI Seminário Integrado de Software e Hardware (SEMISH 2024), pages 252–263. SBC.
Angonese, S. and Galante, R. (2024b). Composition of heterogeneous node embeddings – unlocking the power of heterogeneous graph representation. In Anais do XXXIX Simpósio Brasileiro de Bancos de Dados (SBBD), pages 626–638. SBC.
Angonese, S. F. and Galante, R. (2025). Enhancing graph data quality by leveraging heterogeneous node features and embeddings. In Paes, A. and Verri, F. A. N., editors, Intelligent Systems, pages 383–398. Springer.
Avelar, P. H. C., Tavares, A. R., da Silveira, T. L. T., Jung, C. R., and Lamb, L. C. (2020). Superpixel image classification with graph attention networks. In Proceedings of the 33rd SIBGRAPI Conference on Graphics, Patterns and Images, pages 203–209. IEEE.
Dai, W., Li, J., Li, D., Tiong, A. M. H., Zhao, J., Wang, W., Li, B., Fung, P., and Hoi, S. C. H. (2023). Instructblip: Towards general-purpose vision-language models with instruction tuning. In Proceedings of the Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS). SCITEPRESS.
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), pages 135–144. ACM.
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), pages 2331–2341. ACM.
Guarino, N., Oberle, D., and Staab, S. (2009). What is an ontology? In Staab, S. and Studer, R., editors, Handbook on Ontologies, pages 1–17. Springer.
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 (NeurIPS), pages 1025–1035. Curran Associates, Inc.
Jr., J. A. B., Krogstie, J., Pastor, O., and Pernici, B. (2013). Seminal Contributions to Information Systems Engineering: 25 Years of CAiSE. Springer.
Liebenberg, M. and Jarke, M. (2020). Information systems engineering with digital shadows: Concept and case studies. In Proceedings of the 32nd International Conference on Advanced Information Systems Engineering (CAiSE 2020), pages 70–84. Springer.
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., and Sutskever, I. (2021). Learning transferable visual models from natural language supervision. In Proceedings of the International Conference on Machine Learning (ICML 2021), pages 8748–8763. PMLR.
Rosenkranz, C., Stray, V., and Wiesche, M. (2025). Navigating the new frontier of information systems engineering. In Business & Information Systems Engineering, pages 1–5. Springer.
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. In IEEE Transactions on Big Data, pages 415–436. IEEE.
Zhu, G., Zhu, Z., Chen, H., Yuan, C., and Huang, Y. (2025). Hagnn: Hybrid aggregation for heterogeneous graph neural networks. In IEEE Transactions on Neural Networks and Learning Systems, pages 14536–14550. IEEE.
Angonese, S. and Galante, R. (2024a). AGHE – approach for generating enhanced heterogeneous embeddings from heterogeneous graphs. In Proceedings of the LI Seminário Integrado de Software e Hardware (SEMISH 2024), pages 252–263. SBC.
Angonese, S. and Galante, R. (2024b). Composition of heterogeneous node embeddings – unlocking the power of heterogeneous graph representation. In Anais do XXXIX Simpósio Brasileiro de Bancos de Dados (SBBD), pages 626–638. SBC.
Angonese, S. F. and Galante, R. (2025). Enhancing graph data quality by leveraging heterogeneous node features and embeddings. In Paes, A. and Verri, F. A. N., editors, Intelligent Systems, pages 383–398. Springer.
Avelar, P. H. C., Tavares, A. R., da Silveira, T. L. T., Jung, C. R., and Lamb, L. C. (2020). Superpixel image classification with graph attention networks. In Proceedings of the 33rd SIBGRAPI Conference on Graphics, Patterns and Images, pages 203–209. IEEE.
Dai, W., Li, J., Li, D., Tiong, A. M. H., Zhao, J., Wang, W., Li, B., Fung, P., and Hoi, S. C. H. (2023). Instructblip: Towards general-purpose vision-language models with instruction tuning. In Proceedings of the Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS). SCITEPRESS.
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), pages 135–144. ACM.
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), pages 2331–2341. ACM.
Guarino, N., Oberle, D., and Staab, S. (2009). What is an ontology? In Staab, S. and Studer, R., editors, Handbook on Ontologies, pages 1–17. Springer.
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 (NeurIPS), pages 1025–1035. Curran Associates, Inc.
Jr., J. A. B., Krogstie, J., Pastor, O., and Pernici, B. (2013). Seminal Contributions to Information Systems Engineering: 25 Years of CAiSE. Springer.
Liebenberg, M. and Jarke, M. (2020). Information systems engineering with digital shadows: Concept and case studies. In Proceedings of the 32nd International Conference on Advanced Information Systems Engineering (CAiSE 2020), pages 70–84. Springer.
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., and Sutskever, I. (2021). Learning transferable visual models from natural language supervision. In Proceedings of the International Conference on Machine Learning (ICML 2021), pages 8748–8763. PMLR.
Rosenkranz, C., Stray, V., and Wiesche, M. (2025). Navigating the new frontier of information systems engineering. In Business & Information Systems Engineering, pages 1–5. Springer.
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. In IEEE Transactions on Big Data, pages 415–436. IEEE.
Zhu, G., Zhu, Z., Chen, H., Yuan, C., and Huang, Y. (2025). Hagnn: Hybrid aggregation for heterogeneous graph neural networks. In IEEE Transactions on Neural Networks and Learning Systems, pages 14536–14550. IEEE.
Publicado
19/07/2026
Como Citar
ANGONESE, Silvio Fernando; GALANTE, Renata.
Semantic-Enriched Heterogeneous Embeddings for Enhanced Node Classification. In: SEMINÁRIO INTEGRADO DE SOFTWARE E HARDWARE (SEMISH), 53. , 2026, Gramado/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 626-637.
ISSN 2595-6205.
DOI: https://doi.org/10.5753/semish.2026.23352.
