Vol. 1 No. 4 (2026)

Articles

Neighborhood-Intervention Prediction for Self-Supervised Attributed Graphs

Published 2026-08-30

  • Daniel Teixeira Rocha
    • ,
  • Felipe L. Melo Pires

Daniel Teixeira Rocha
Department of Computer and Digital Systems Engineering, Polytechnic School, Universidade de São Paulo, São Paulo, Brazil

Felipe L. Melo Pires
Department of Computer and Digital Systems Engineering, Polytechnic School, Universidade de São Paulo, São Paulo, Brazil

Language, Knowledge and Intelligent Systems, Volume 1, Issue 4, 2026 cover

Abstract

The rapid evolution of graph representation learning has fundamentally transformed the analysis of interconnected data structures, ranging from molecular configurations to expansive social networks. Despite the profound success of message-passing architectures, contemporary models predominantly rely on observational neighborhood aggregations, rendering them vulnerable to spurious correlations, structural noise, and the pervasive issue of over-smoothing. To address these critical limitations, this paper introduces a novel self-supervised learning paradigm designated as Neighborhood-Intervention Prediction for attributed graphs. Grounded in the principles of causal inference, our framework systematically applies structural and feature-based interventions to the local subgraphs of target nodes. By compelling the neural encoder to predict the original, unperturbed neighborhood context from an explicitly intervened state, the model learns robust, causal-aware node representations that generalize effectively under distribution shifts. This research thoroughly articulates the theoretical underpinnings of graph-based interventions, detailing a methodology that bypasses the need for manual annotations through a fully self-supervised predictive objective. Extensive empirical evaluations across multiple benchmark datasets demonstrate that the proposed framework consistently surpasses traditional contrastive and generative baselines in downstream tasks, notably node classification and link prediction. Furthermore, structural sensitivity analyses reveal that our intervention strategy significantly mitigates the assimilation of noisy edges and preserves local topological heterogeneity. Ultimately, this work establishes a robust foundation for integrating causal reasoning into self-supervised graph neural networks.

Keywords

Graph Neural Networks, Self-Supervised Learning, Causal Inference, Representation Learning, Attributed Graphs

PDF

References

  1. 1. Zhao, R., Zeng, W., Tang, J., Li, Y., Ye, G., Du, J., & Zhao, X. (2025, May). Towards unsupervised entity alignment for highly heterogeneous knowledge graphs. In 2025 IEEE 41St international conference on data engineering (ICDE) (pp. 3792-3806). IEEE.
  2. 2. Zhao, R., Zeng, W., Zhang, W., Zhao, X., Tang, J., & Chen, L. (2025). Towards temporal knowledge graph alignment in the wild. arXiv preprint arXiv:2507.14475.
  3. 3. Lee, Y., Xu, Y., Gao, P., & Chen, J. (2024). Tenet: triple-enhancement based graph neural network for cell-cell interaction network reconstruction from spatial transcriptomics. Journal of Molecular Biology, 436 (9), 168543.
  4. 4. Fang, R., Chen, C., Wang, Q., Ling, C., Wang, B., & Zhang, H. (2026). Transfer learning with graph neural networks to predict polymer solubility parameters. npj Computational Materials.
  5. 5. Hamilton, W., Ying, Z., & Leskovec, J. (2017). Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems.
  6. 6. Li, B., Zhang, R., Liang, H., Zhang, J., Zhang, J., Chen, X., ... & Wang, J. (2026). Interagent: Physics-based multi-agent command execution via diffusion on interaction graphs. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 15253-15265).
  7. 7. Yu, H., Zhang, J., Chen, C., Xiang, T., Fang, Y., Niebles, J. C., & Adeli, E. (2026, March). Socialgen: Modeling multi-human social interaction with language models. In 2026 International Conference on 3D Vision (3DV) (pp. 1-17). IEEE.
  8. 8. Yao, Y., Sun, J., Miao, P., Chen, G., & Tafazolli, R. (2026). Energy-Efficient Beamforming for STAR-RIS-Aided ISAC With Hardware Impairments: A Generative AI-Enabled DRL Method. IEEE Transactions on Wireless Communications.
  9. 9. Song, S., Huang, D., Deng, D., Xiong, H., Tang, Y., Zhao, Y., & Qin, R. (2026). Olbedo: An Albedo and Shading Aerial Dataset for Large-Scale Outdoor Environments. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 6474-6483).
  10. 10. Yao, Y., Xiao, W., Miao, P., Chen, G., Yang, H., Chae, C. B., & Wong, K. K. (2026). UAV-RHS-enabled full-duplex ISAC covert system: Robust beamforming and trajectory optimization. IEEE Transactions on Communications.
  11. 11. Yao, Y., Xiao, W., Miao, P., Chen, G., Yang, H., Chae, C. B., & Wong, K. K. (2025). UAV-relay-aided secure maritime networks coexisting with satellite networks: robust beamforming and trajectory optimization. IEEE Transactions on Wireless Communications.
  12. 12. Wang, X., Ma, X., Zhu, P., Ng, W. S., Zhang, H., Xia, X., ... & Au, K. W. S. (2024). Design, optimization, and experimental validation of a handheld nonconstant-curvature hybrid-structure robotic instrument for maxillary sinus surgery. IEEE/ASME Transactions on Mechatronics, 29(4), 3074-3082.
  13. 13. Mo, Z. (2025, May). Development of an Intelligent Retrieval and Recommendation System for Chinese Language Educational Resources Based on DNN Technology. In 2025 2nd International Conference on Intelligent Computing and Robotics (ICICR) (pp. 170-175). IEEE.
  14. 14. Yu, X., Wei, Y., Zhou, S., Yang, Z., Sun, L., Peng, H., ... & Yu, P. S. (2025, April). Towards effective, efficient and unsupervised social event detection in the hyperbolic space. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 12, pp. 13106-13114).
  15. 15. Zhang, Z., Ren, F., Zhang, J., Su, S., Yan, Y., Wei, Q., ... & Guo, C. (2022). When behavior analysis meets social network alignment. IEEE Transactions on Knowledge and Data Engineering, 35(7), 7590-7607.
  16. 16. Xiong, F., Xu, H., Wang, Y., Cheng, R., Wang, Y., & Chu, X. (2025, November). Hs-star: Hierarchical sampling for self-taught reasoners via difficulty estimation and budget reallocation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (pp. 5539-5555).
  17. 17. Wei, Q., Li, R., Bai, W., & Han, Z. (2025). Multi-UAV-enabled energy-efficient data delivery for low-altitude economy: Joint coded caching, user grouping, and UAV deployment. IEEE Internet of Things Journal, 12(14), 27519-27532.
  18. 18. Li, R., Xiao, Z., & Zeng, Y. (2023). Toward seamless sensing coverage for cellular multi-static integrated sensing and communication. IEEE Transactions on Wireless Communications, 23(6), 5363-5376.
  19. 19. Li, Q., Ye, Q., Zhang, N., Zhang, W., & Hu, F. (2025). Digital-twin-enabled industrial IoT: Vision, framework, and future directions. IEEE Wireless Communications, 32(6), 173-181.
  20. 20. Li, Y. Z., Zhang, J. P., Chen, Z. Y., Wang, H. C., Zhang, K. X., Hu, S. S., ... & Dudley, M. (2026, September). Growth and Characterization of High-Quality Thick Epitaxial 4H-SiC Wafers for High Voltage Devices. In Defect and Diffusion Forum (Vol. 452, pp. 79-85). Trans Tech Publications Ltd.
  21. 21. Li, S. (2025). Momentum, volume and investor sentiment study for us technology sector stocks—A hidden markov model based principal component analysis. PloS one, 20(9), e0331658.
  22. 22. Li, X., Wang, P., Li, G., Ni, L., & Zhang, Y. (2023). Design of interface circuits and lightweight PUF for TMR sensors. IEEE Sensors Journal, 23(11), 11754-11761.
  23. 23. Liang, R., Xu, S., Xie, C., Chen, J., Ren, F., Yang, S., & Yabe, T. (2026). Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency. Advances in Neural Information Processing Systems, 38, 99445-99471.
  24. 24. Liu, X., Yu, Z., Yao, Y., Yang, K., Zeng, H., & Chen, C. P. (2026). A Comprehensive Survey of Cross-Modal Retrieval: Breaking Through Modal Barriers. ACM Computing Surveys.
  25. 25. Zhang, Q., Yang, M., Sun, G., Xiang, Y., Wang, S., Zhang, J., & Li, S. (2026). Representation learning accelerates the development of models for Li-ion battery health diagnostics and prognostics. Energy Storage Materials, 104897.
  26. 26. Wang, Z., Yuan, R., Geng, Z., Li, H., Qu, X., Li, X., ... & Zhang, K. (2025, October). Singing timbre popularity assessment based on multimodal large foundation model. In Proceedings of the 33rd ACM International Conference on Multimedia (pp. 12227-12236).
  27. 27. Ghosh, R., Jia, X., Yin, L., Lin, C., Jin, Z., & Kumar, V. (2022, November). Clustering augmented self-supervised learning: an application to land cover mapping. In Proceedings of the 30th International Conference on Advances in Geographic Information Systems (pp. 1-10).
  28. 28. Wang, Jiacheng, et al. "A Dynamic Factor Gating Architecture with Market Regime Awareness for Stock Return Forecasting." (2026).
  29. 29. Lyu, M., Torii, R., Liang, C., Peach, T. W., Bhogal, P., Makalanda, L., ... & Chen, D. (2024). Treatment for middle cerebral artery bifurcation aneurysms: in silico comparison of the novel Contour device and conventional flow-diverters. Biomechanics and Modeling in Mechanobiology, 23(4), 1149-1160.
  30. 30. Wang, Y., & Ling, C. (2025). Comparing SAS® and R Approaches in Reshaping data. In PharmaSUG 2025 Conference Proceedings.
  31. 31. Hu, J., Dowell, N., Brooks, C., & Yan, W. (2018, June). Temporal changes in affiliation and emotion in MOOC discussion forum discourse. In International conference on artificial intelligence in education (pp. 145-149). Cham: Springer International Publishing.