One-Class Learning for Graph Neural Networks
Resumo
One-Class Learning (OCL) for graphs addresses problems in which only nodes from a class of interest are available for training, while the remaining graph nodes space is broad, unknown, or continuously evolving. Although Graph Neural Networks (GNNs) provide a natural mechanism for exploiting relational information, existing one-class approaches still present limitations regarding end-to-end optimization, interpretability, graph streams, edge-level prediction, and heterogeneous structures. This thesis introduces the OLGA family, a set of end-to-end, one-class, GNN-interpretable methods. OLGA establishes the methodological core by combining a novel sphere-based loss, which continuously compacts interest nodes in a low-dimensional latent space, with graph autoencoder reconstruction. OLGASTREAM extends the thesis to stream graphs by weighting the losses and employing FAConv to mitigate concept drift. ECHOLGA extends the thesis to causal edge classification by transforming relations into nodes of a heterogeneous hypergraph. FOLGA addresses heterogeneous node classification through topology rewiring and layer-wise fusion. Experiments on 19 datasets from textual, visual, tabular, streaming, causal, and heterogeneous domains show that the proposed methods achieved the best f1−macro in 14. Overall, the thesis advances the field of OCL for GNNs.
Referências
Bing, R., Yuan, G., Zhu, M., Meng, F., Ma, H., and Qiao, S. (2023). Heterogeneous graph neural networks analysis: a survey of techniques, evaluations and applications. Artificial Intelligence Review, 56(8):8003–8042.
Chen, A., Wu, J., and Zhang, H. (2025). Fiad: Graph anomaly detection framework based feature injection. Expert Systems with Applications, 259:125216.
Coutinho, G., Lima, A., Yugoshi, J., Moraes Junior, M., Gôlo, M., and Marcacini, R. (2023). Multimodal audio emotion recognition with graph-based consensus pseudolabeling. In Proceedings of the National Meeting on Artificial and Computational Intelligence, Porto Alegre, RS, Brasil. SBC.
da Silva, A., Gôlo, M., and Marcacini, R. (2022). Unsupervised heterogeneous graph neural network for hit song prediction through one class learning. In Proceedings of the Symposium on Knowledge Discovery, Mining and Learning, Porto Alegre, RS, Brasil. SBC.
de Souza, M. C., Gôlo, M. P. S., Jorge, A. M. G., de Amorim, E. C. F., Campos, R. N. T., Marcacini, R. M., and Rezende, S. O. (2024). Keywords attention for fake news detection using few positive labels. Information Sciences, 663:120300.
Deldar, F., Abadi, M., and Ebrahimifard, M. (2022). Android malware detection using one-class graph neural networks. ISeCure, 14(3).
Diestel, R. (2025). Graph theory. Springer, Berlin, Germany.
do Carmo, P. V., Silva Gôlo, M. P., Gwozdz, J., Marx, E., and Marcondes Marcacini, R. (2025). Improving natural product knowledge extraction from academic literature with enhanced pdf text extraction and large language models. In Proceedings of the Symposium on Applied Computing, pages 980–987, New York, NY, USA. ACM.
Dou, Y., Liu, Z., Sun, L., Deng, Y., Peng, H., and Yu, P. S. (2020). Enhancing graph neural network-based fraud detectors against camouflaged fraudsters. In Proceedings of the International Conference on Information & Knowledge Management, pages 315–324, New York, NY, USA. ACM.
Emmert-Streib, F. and Dehmer, M. (2022). Taxonomy of machine learning paradigms: A data-centric perspective. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, page e1470.
Fan, H., Wang, R., Huang, X., Zhang, F., Li, Z., and Su, S. (2024). Deep joint adversarial learning for anomaly detection on attribute networks. Information Sciences, 654:119840.
Feng, Y., Chen, J., Liu, Z., Lv, H., and Wang, J. (2022). Full graph autoencoder for one-class group anomaly detection of iiot system. Internet of Things Journal.
Filho, I. J. R., Gôlo, M. P., Marcacini, R. M., and Rezende, S. O. (2025). How do financial time series enhance the detection of news significance in market movements? a study using graph neural networks with heterogeneous representations. Neural Computing and Applications, 37(3):1307–1319.
Ganz, T., Ashraf, I., Härterich, M., and Rieck, K. (2023). Detecting backdoors in collaboration graphs of software repositories. In Proceedings of the Conference on Data and Application Security and Privacy, pages 189–200, New York, NY, USA. ACM.
Gkarmpounis, G., Vranis, C., Vretos, N., and Daras, P. (2024). Survey on graph neural networks. IEEE Access.
Gôlo, M., Moraes, L., Goularte, R., and Marcacini, R. (2022). One-class recommendation through unsupervised graph neural networks for link prediction. In Proceedings of the Symposium on Knowledge Discovery, Mining and Learning, pages 146–153, Porto Alegre, RS, Brazil. SBC.
Gôlo, M., Moraes Junior, M., Goularte, R., and Marcacini, R. (2023a). On the use of early fusion operators on heterogeneous graph neural networks for one-class learning. In Proceedings of the Brazilian Symposium on Multimedia and the Web, New York, NY, USA. ACM.
Gôlo, M. P., Mori, A. L., Oliveira, W. G., Barbosa, J. R., Graciano-Neto, V. V., de Lima, E. A., and Marcacini, R. M. (2024a). On the use of large language models to detect brazilian politics fake news. In Proceedings of the National Meeting on Artificial and Computational Intelligence, pages 1–12, Porto Alegre, RS, Brasil. SBC.
Gôlo, M. P. S., de Medeiros Junior, J. G. B., Silva, D. F., and Marcacini, R. M. (2025a). One-class graph autoencoder: A new end-to-end, low-dimensional, and interpretable approach for node classification. Information Sciences, page 122060.
Gôlo, M. P. S., de Medeiros Junior, J. G. B., Vilas Boas, G. S., Lobato, F. M. F., Silva, D. F., and Marcacini, R. M. (2025b). Large language models ensemble for biochemical properties detection in scientific articles. In Proceedings of the Text2KG Workshop at European Semantic Web Conference, Aachen, Germany. CEUR-WS.
Gôlo, M. P. S., de Moraes, L. G., Goularte, R., and Marcacini, R. M. (2024b). The impact of representation learning on unsupervised graph neural networks for one-class recommendation. Journal of Information and Data Management, 15(1):112–122.
Gôlo, M. P. S., de Moraes Junior, M. I., Goularte, R., and Marcacini, R. M. (2024c). Unsupervised heterogeneous graph neural networks for one-class tasks: Exploring early fusion operators. Journal on Interactive Systems, 15(1):517–529.
Gôlo, M. P. S., de Souza, M. C., Rossi, R. G., Rezende, S. O., Nogueira, B. M., and Marcacini, R. M. (2023b). One-class learning for fake news detection through multimodal variational autoencoders. Engineering Applications of Artificial Intelligence, 122:106088.
Gôlo, M. P. S., Gama, J., and Marcacini, R. M. (2024d). One-class learning for data stream through graph neural networks. In Proceedings of the Brazilian Conference on Intelligent Systems, pages 61–75, Cham, Switzerland. Springer.
Gôlo, M. P. S. and Marcacini, R. M. (2024). One-class learning for text causal discovery through hypergraph neural networks. In Proceedings of the Workshop on Causal Discovery, pages 1–12.
Gôlo, M. P. S. and Marcacini, R. M. (2025). One-class edge classification through heterogeneous hypergraph for causal discovery. Scientific Reports.
Gôlo, M. P. S. and Utino, M. Y. R. (2025). One-class lightweight interpretable filtering for academic profiles and strategic themes affinity. In Proceedings of the International Symposium on Computer Architecture and High Performance Computing Workshops, pages 147–154, Piscataway, NJ, USA. IEEE.
Gôlo, M., Gama, J., Marx, E., and Marcacini, R. (2026). Fusion-rewired one class graph autoencoder. In Proceedings of the International Joint Conference on Neural Networks, Piscataway, NJ, USA. IEEE. Accepted for publication.
Hassanzadeh, O., Bhattacharjya, D., Feblowitz, M., Srinivas, K., Perrone, M., Sohrabi, S., and Katz, M. (2019). Answering binary causal questions through large-scale text mining an evaluation using cause-effect pairs from human experts. In Proceedings of the International Joint Conferences on Artificial Intelligence, pages 5003–5009, Washington, DC, USA. AAAI.
Hu, J., Xiao, B., Jin, H., Duan, J., Wang, S., Lv, Z., Wang, S., Liu, X., and Zhu, E. (2023). Samcl: Subgraph-aligned multiview contrastive learning for graph anomaly detection. Transactions on Neural Networks and Learning Systems.
Huang, B., Wang, X., Cui, P., Jiang, W., Yang, Y., and Fan, Q. (2021). One-class temporal graph attention neural network for dynamic graph anomaly detection. In Proceedings of the International Conference on Electronics, Communications and Information Technology, pages 783–790, Piscataway, NJ, USA. IEEE.
Huang, Z., Gu, Y., and Zhao, Q. (2022). One-class directed heterogeneous graph neural network for intrusion detection. In Proceedings of the International Conference on Innovation in Artificial Intelligence, pages 178–184, New York, NY, USA. ACM.
Jodelka, O., Anagnostopoulos, C., and Kolomvatsos, K. (2021). Adaptive novelty detection over contextual data streams at the edge using one-class classification. In Proceedings of the International Conference on Information and Communication Systems, Piscataway, NJ, USA. IEEE.
Kayesh, H., Islam, M. S., and Wang, J. (2023). Answering binary causal questions using role-oriented concept embedding. Transactions on Artificial Intelligence, 4(06):1426–1436.
Kayesh, H., Islam, M. S., Wang, J., Anirban, S., Kayes, A., and Watters, P. (2020). Answering binary causal questions: A transfer learning based approach. In Proceedings of the International Joint Conference on Neural Networks, pages 1–9, Piscataway, NJ, USA. IEEE.
Khemani, B., Patil, S., Kotecha, K., and Tanwar, S. (2024). A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions. Journal of Big Data, 11(1):18.
Li, Q., Wu, G., Ni, H., and You, T. (2024). Anomaly detection with dual-channel heterogeneous graph based on hypersphere learning. Information Sciences, 681:121242.
Liu, X., Xu, P., Wu, J., Yuan, J., Yang, Y., Zhou, Y., Liu, F., Guan, T., Wang, H., Yu, T., et al. (2024). Large language models and causal inference in collaboration: A comprehensive survey. arXiv preprint arXiv:2403.09606.
Marx, E., do Carmo, P. V., Gôlo, M., and Tramp, S., editors (2025). Preface of the First International TEXT2SPARQL Challenge (TEXT2SPARQL’25), Aachen, Germany. CEUR-WS.
Mendelson, S. and Lerner, B. (2020). Online cluster drift detection for novelty detection in data streams. In Proceedings of the International Conference on Machine Learning and Applications, Piscataway, NJ, USA. IEEE.
Miranda, A. C. D., Utino, M. Y. R., Gôlo, M. P. S., Santos, M. A. A. D., and de Souza, M. C. (2025). Reducing costs in large-scale classification: A hybrid bert–llm strategy. In Proceedings of the International Symposium on Computer Architecture and High Performance Computing Workshops, pages 131–138, Piscataway, NJ, USA. IEEE.
Nguyen, T. and Grishman, R. (2018). Graph convolutional networks with argument-aware pooling for event detection. In Proceedings of the Conference on Artificial Intelligence, Washington, DC, USA. AAAI.
Seliya, N., Abdollah Zadeh, A., and Khoshgoftaar, T. M. (2021). A literature review on one-class classification and its potential applications in big data. Journal of Big Data, 8:1–31.
Shi, B., Dong, B., Xu, Y., Wang, J., Wang, Y., and Zheng, Q. (2023). An edge feature aware heterogeneous graph neural network model to support tax evasion detection. Expert Systems with Applications, 213:118903.
Tax, D. M. J. (2001). One-class classification: Concept learning in the absence of counter-examples. PhD thesis, Technische Universiteit Delft.
Utino, M. Y. R. and Gôlo, M. P. S. (2025). Efficient filtering with bert embeddings for researcher–topic affinity prediction in hpc pipelines. In Proceedings of the International Symposium on Computer Architecture and High Performance Computing Workshops, pages 155–162, Piscataway, NJ, USA. IEEE.
Veličković, P. (2023). Everything is connected: Graph neural networks. Current Opinion in Structural Biology, 79:102538.
Wang, X., Bo, D., Shi, C., Fan, S., Ye, Y., and Philip, S. Y. (2022). A survey on heterogeneous graph embedding: methods, techniques, applications and sources. Transactions on Big Data, 9:415 – 436.
Wang, X., Jin, B., Du, Y., Cui, P., Tan, Y., and Yang, Y. (2021). One-class graph neural networks for anomaly detection in attributed networks. Neural Computing and Applications, 33(18):12073–12085.
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., and Philip, S. Y. (2020). A comprehensive survey on graph neural networks. Transactions on Neural Networks and Learning Systems, 32(1):4–24.
Zadeh, A. A. (2024). Advancing One-Class Classification: A Comprehensive Analysis From Theory To Novel Applications. PhD thesis, Florida Atlantic University Boca Raton, FL.
Zhang, F., Fan, H., Wang, R., Li, Z., and Liang, T. (2022a). Deep dual support vector data description for anomaly detection on attributed networks. International Journal of Intelligent Systems, 37(2):1509–1528.
Zhang, J., Wang, X., Yu, Z., Huang, M., Duan, L., and Zuo, J. (2022b). Steam: Svdd-based anomaly detection on attributed networks via multi-autoencoders. In Proceedings of the International Conference on High Performance Computing and Communications, pages 595–602, Piscataway, NJ, USA. IEEE.
Chen, A., Wu, J., and Zhang, H. (2025). Fiad: Graph anomaly detection framework based feature injection. Expert Systems with Applications, 259:125216.
Coutinho, G., Lima, A., Yugoshi, J., Moraes Junior, M., Gôlo, M., and Marcacini, R. (2023). Multimodal audio emotion recognition with graph-based consensus pseudolabeling. In Proceedings of the National Meeting on Artificial and Computational Intelligence, Porto Alegre, RS, Brasil. SBC.
da Silva, A., Gôlo, M., and Marcacini, R. (2022). Unsupervised heterogeneous graph neural network for hit song prediction through one class learning. In Proceedings of the Symposium on Knowledge Discovery, Mining and Learning, Porto Alegre, RS, Brasil. SBC.
de Souza, M. C., Gôlo, M. P. S., Jorge, A. M. G., de Amorim, E. C. F., Campos, R. N. T., Marcacini, R. M., and Rezende, S. O. (2024). Keywords attention for fake news detection using few positive labels. Information Sciences, 663:120300.
Deldar, F., Abadi, M., and Ebrahimifard, M. (2022). Android malware detection using one-class graph neural networks. ISeCure, 14(3).
Diestel, R. (2025). Graph theory. Springer, Berlin, Germany.
do Carmo, P. V., Silva Gôlo, M. P., Gwozdz, J., Marx, E., and Marcondes Marcacini, R. (2025). Improving natural product knowledge extraction from academic literature with enhanced pdf text extraction and large language models. In Proceedings of the Symposium on Applied Computing, pages 980–987, New York, NY, USA. ACM.
Dou, Y., Liu, Z., Sun, L., Deng, Y., Peng, H., and Yu, P. S. (2020). Enhancing graph neural network-based fraud detectors against camouflaged fraudsters. In Proceedings of the International Conference on Information & Knowledge Management, pages 315–324, New York, NY, USA. ACM.
Emmert-Streib, F. and Dehmer, M. (2022). Taxonomy of machine learning paradigms: A data-centric perspective. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, page e1470.
Fan, H., Wang, R., Huang, X., Zhang, F., Li, Z., and Su, S. (2024). Deep joint adversarial learning for anomaly detection on attribute networks. Information Sciences, 654:119840.
Feng, Y., Chen, J., Liu, Z., Lv, H., and Wang, J. (2022). Full graph autoencoder for one-class group anomaly detection of iiot system. Internet of Things Journal.
Filho, I. J. R., Gôlo, M. P., Marcacini, R. M., and Rezende, S. O. (2025). How do financial time series enhance the detection of news significance in market movements? a study using graph neural networks with heterogeneous representations. Neural Computing and Applications, 37(3):1307–1319.
Ganz, T., Ashraf, I., Härterich, M., and Rieck, K. (2023). Detecting backdoors in collaboration graphs of software repositories. In Proceedings of the Conference on Data and Application Security and Privacy, pages 189–200, New York, NY, USA. ACM.
Gkarmpounis, G., Vranis, C., Vretos, N., and Daras, P. (2024). Survey on graph neural networks. IEEE Access.
Gôlo, M., Moraes, L., Goularte, R., and Marcacini, R. (2022). One-class recommendation through unsupervised graph neural networks for link prediction. In Proceedings of the Symposium on Knowledge Discovery, Mining and Learning, pages 146–153, Porto Alegre, RS, Brazil. SBC.
Gôlo, M., Moraes Junior, M., Goularte, R., and Marcacini, R. (2023a). On the use of early fusion operators on heterogeneous graph neural networks for one-class learning. In Proceedings of the Brazilian Symposium on Multimedia and the Web, New York, NY, USA. ACM.
Gôlo, M. P., Mori, A. L., Oliveira, W. G., Barbosa, J. R., Graciano-Neto, V. V., de Lima, E. A., and Marcacini, R. M. (2024a). On the use of large language models to detect brazilian politics fake news. In Proceedings of the National Meeting on Artificial and Computational Intelligence, pages 1–12, Porto Alegre, RS, Brasil. SBC.
Gôlo, M. P. S., de Medeiros Junior, J. G. B., Silva, D. F., and Marcacini, R. M. (2025a). One-class graph autoencoder: A new end-to-end, low-dimensional, and interpretable approach for node classification. Information Sciences, page 122060.
Gôlo, M. P. S., de Medeiros Junior, J. G. B., Vilas Boas, G. S., Lobato, F. M. F., Silva, D. F., and Marcacini, R. M. (2025b). Large language models ensemble for biochemical properties detection in scientific articles. In Proceedings of the Text2KG Workshop at European Semantic Web Conference, Aachen, Germany. CEUR-WS.
Gôlo, M. P. S., de Moraes, L. G., Goularte, R., and Marcacini, R. M. (2024b). The impact of representation learning on unsupervised graph neural networks for one-class recommendation. Journal of Information and Data Management, 15(1):112–122.
Gôlo, M. P. S., de Moraes Junior, M. I., Goularte, R., and Marcacini, R. M. (2024c). Unsupervised heterogeneous graph neural networks for one-class tasks: Exploring early fusion operators. Journal on Interactive Systems, 15(1):517–529.
Gôlo, M. P. S., de Souza, M. C., Rossi, R. G., Rezende, S. O., Nogueira, B. M., and Marcacini, R. M. (2023b). One-class learning for fake news detection through multimodal variational autoencoders. Engineering Applications of Artificial Intelligence, 122:106088.
Gôlo, M. P. S., Gama, J., and Marcacini, R. M. (2024d). One-class learning for data stream through graph neural networks. In Proceedings of the Brazilian Conference on Intelligent Systems, pages 61–75, Cham, Switzerland. Springer.
Gôlo, M. P. S. and Marcacini, R. M. (2024). One-class learning for text causal discovery through hypergraph neural networks. In Proceedings of the Workshop on Causal Discovery, pages 1–12.
Gôlo, M. P. S. and Marcacini, R. M. (2025). One-class edge classification through heterogeneous hypergraph for causal discovery. Scientific Reports.
Gôlo, M. P. S. and Utino, M. Y. R. (2025). One-class lightweight interpretable filtering for academic profiles and strategic themes affinity. In Proceedings of the International Symposium on Computer Architecture and High Performance Computing Workshops, pages 147–154, Piscataway, NJ, USA. IEEE.
Gôlo, M., Gama, J., Marx, E., and Marcacini, R. (2026). Fusion-rewired one class graph autoencoder. In Proceedings of the International Joint Conference on Neural Networks, Piscataway, NJ, USA. IEEE. Accepted for publication.
Hassanzadeh, O., Bhattacharjya, D., Feblowitz, M., Srinivas, K., Perrone, M., Sohrabi, S., and Katz, M. (2019). Answering binary causal questions through large-scale text mining an evaluation using cause-effect pairs from human experts. In Proceedings of the International Joint Conferences on Artificial Intelligence, pages 5003–5009, Washington, DC, USA. AAAI.
Hu, J., Xiao, B., Jin, H., Duan, J., Wang, S., Lv, Z., Wang, S., Liu, X., and Zhu, E. (2023). Samcl: Subgraph-aligned multiview contrastive learning for graph anomaly detection. Transactions on Neural Networks and Learning Systems.
Huang, B., Wang, X., Cui, P., Jiang, W., Yang, Y., and Fan, Q. (2021). One-class temporal graph attention neural network for dynamic graph anomaly detection. In Proceedings of the International Conference on Electronics, Communications and Information Technology, pages 783–790, Piscataway, NJ, USA. IEEE.
Huang, Z., Gu, Y., and Zhao, Q. (2022). One-class directed heterogeneous graph neural network for intrusion detection. In Proceedings of the International Conference on Innovation in Artificial Intelligence, pages 178–184, New York, NY, USA. ACM.
Jodelka, O., Anagnostopoulos, C., and Kolomvatsos, K. (2021). Adaptive novelty detection over contextual data streams at the edge using one-class classification. In Proceedings of the International Conference on Information and Communication Systems, Piscataway, NJ, USA. IEEE.
Kayesh, H., Islam, M. S., and Wang, J. (2023). Answering binary causal questions using role-oriented concept embedding. Transactions on Artificial Intelligence, 4(06):1426–1436.
Kayesh, H., Islam, M. S., Wang, J., Anirban, S., Kayes, A., and Watters, P. (2020). Answering binary causal questions: A transfer learning based approach. In Proceedings of the International Joint Conference on Neural Networks, pages 1–9, Piscataway, NJ, USA. IEEE.
Khemani, B., Patil, S., Kotecha, K., and Tanwar, S. (2024). A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions. Journal of Big Data, 11(1):18.
Li, Q., Wu, G., Ni, H., and You, T. (2024). Anomaly detection with dual-channel heterogeneous graph based on hypersphere learning. Information Sciences, 681:121242.
Liu, X., Xu, P., Wu, J., Yuan, J., Yang, Y., Zhou, Y., Liu, F., Guan, T., Wang, H., Yu, T., et al. (2024). Large language models and causal inference in collaboration: A comprehensive survey. arXiv preprint arXiv:2403.09606.
Marx, E., do Carmo, P. V., Gôlo, M., and Tramp, S., editors (2025). Preface of the First International TEXT2SPARQL Challenge (TEXT2SPARQL’25), Aachen, Germany. CEUR-WS.
Mendelson, S. and Lerner, B. (2020). Online cluster drift detection for novelty detection in data streams. In Proceedings of the International Conference on Machine Learning and Applications, Piscataway, NJ, USA. IEEE.
Miranda, A. C. D., Utino, M. Y. R., Gôlo, M. P. S., Santos, M. A. A. D., and de Souza, M. C. (2025). Reducing costs in large-scale classification: A hybrid bert–llm strategy. In Proceedings of the International Symposium on Computer Architecture and High Performance Computing Workshops, pages 131–138, Piscataway, NJ, USA. IEEE.
Nguyen, T. and Grishman, R. (2018). Graph convolutional networks with argument-aware pooling for event detection. In Proceedings of the Conference on Artificial Intelligence, Washington, DC, USA. AAAI.
Seliya, N., Abdollah Zadeh, A., and Khoshgoftaar, T. M. (2021). A literature review on one-class classification and its potential applications in big data. Journal of Big Data, 8:1–31.
Shi, B., Dong, B., Xu, Y., Wang, J., Wang, Y., and Zheng, Q. (2023). An edge feature aware heterogeneous graph neural network model to support tax evasion detection. Expert Systems with Applications, 213:118903.
Tax, D. M. J. (2001). One-class classification: Concept learning in the absence of counter-examples. PhD thesis, Technische Universiteit Delft.
Utino, M. Y. R. and Gôlo, M. P. S. (2025). Efficient filtering with bert embeddings for researcher–topic affinity prediction in hpc pipelines. In Proceedings of the International Symposium on Computer Architecture and High Performance Computing Workshops, pages 155–162, Piscataway, NJ, USA. IEEE.
Veličković, P. (2023). Everything is connected: Graph neural networks. Current Opinion in Structural Biology, 79:102538.
Wang, X., Bo, D., Shi, C., Fan, S., Ye, Y., and Philip, S. Y. (2022). A survey on heterogeneous graph embedding: methods, techniques, applications and sources. Transactions on Big Data, 9:415 – 436.
Wang, X., Jin, B., Du, Y., Cui, P., Tan, Y., and Yang, Y. (2021). One-class graph neural networks for anomaly detection in attributed networks. Neural Computing and Applications, 33(18):12073–12085.
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., and Philip, S. Y. (2020). A comprehensive survey on graph neural networks. Transactions on Neural Networks and Learning Systems, 32(1):4–24.
Zadeh, A. A. (2024). Advancing One-Class Classification: A Comprehensive Analysis From Theory To Novel Applications. PhD thesis, Florida Atlantic University Boca Raton, FL.
Zhang, F., Fan, H., Wang, R., Li, Z., and Liang, T. (2022a). Deep dual support vector data description for anomaly detection on attributed networks. International Journal of Intelligent Systems, 37(2):1509–1528.
Zhang, J., Wang, X., Yu, Z., Huang, M., Duan, L., and Zuo, J. (2022b). Steam: Svdd-based anomaly detection on attributed networks via multi-autoencoders. In Proceedings of the International Conference on High Performance Computing and Communications, pages 595–602, Piscataway, NJ, USA. IEEE.
Publicado
19/10/2026
Como Citar
GÔLO, Marcos Paulo Silva.
One-Class Learning for Graph Neural Networks. In: CONCURSO DE TESES E DISSERTAÇÕES EM INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (CTDIAC), 15. , 2026, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 97-114.
DOI: https://doi.org/10.5753/ctdiac.2026.27588.
