Label-Efficient Node Inference with Curvature-Gated Spiking Dynamics
Main Article Content
Abstract
The exponential growth of graph-structured data across diverse domains has necessitated the development of highly efficient node inference algorithms. Traditional graph neural networks often struggle with label scarcity and incur substantial computational overhead during training and inference, limiting their deployment in resource-constrained environments. This paper proposes a novel framework, Curvature-Gated Spiking Dynamics, which synergizes the energy efficiency of neuromorphic computing with the structural awareness of discrete graph geometry. By leveraging discrete curvature metrics to dynamically modulate the firing thresholds of a spiking neural network, the proposed architecture effectively mitigates the over-squashing phenomenon and enhances information propagation across heterogeneous graph topologies. We present a comprehensive theoretical and empirical analysis of the curvature-gating mechanism, demonstrating its capacity to achieve robust label-efficient node inference. Extensive qualitative and quantitative evaluations indicate that the integration of geometric priors into spiking dynamics significantly improves classification accuracy under extreme label sparsity while drastically reducing energy consumption compared to conventional continuous-time models. The findings highlight the potential of combining structural graph properties with biologically plausible neural dynamics to advance the next generation of sustainable and scalable machine learning systems.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in the Journal of the Artificial Intelligence Engineers Consortium (JAIEC) are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, reproduction, and adaptation in any medium, provided the original author(s) and source are properly credited.
Authors retain copyright of their work while granting the journal the right of first publication.
References
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. 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.
3. Fang, R., Zhao, J., Wang, S., Pu, R., Li, B., Cai, J., ... & Wang, B. (2025). Saga: Structural aggregation guided alignment with dynamic view and neighborhood order selection for multiview graph domain adaptation. In The Fourteenth International Conference on Learning Representations.
4. Hamilton, W., Ying, Z., & Leskovec, J. (2017). Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems.
5. Zhao, R., Tang, J., Zeng, W., Guo, Y., & Zhao, X. (2025). Towards human-like questioning: Knowledge base question generation with bias-corrected reinforcement learning from human feedback. Information Processing & Management, 62(3), 104044.
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. 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).
8. Li, R., Wang, Y., Wang, C., Chen, J., Wu, D., Han, G., & Zeng, Y. (2026). Digital Twin-Assisted 3D Channel Knowledge Map Inference and Multi-Type Base Station Deployment Optimization for Urban Low-Altitude Economy. IEEE Transactions on Mobile Computing.
9. 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.
10. Yao, Y., Zhang, J., Miao, P., Zhang, L., Chen, G., Shu, F., & Wong, K. K. (2025). Hybrid RIS-enhanced ISAC secure systems: Joint optimization in the presence of an extended target. IEEE Transactions on Communications.
11. Li, R., Wang, L., Chen, K., Xu, L., & Fei, A. (2024). Full-duplex NOMA-enabled integrated sensing and communication: Joint transmit and receive beamforming optimization. IEEE Internet of Things Journal, 11(16), 27015-27029.
12. Yao, Y., Zhu, Z., Miao, P., Cheng, X., Shu, F., & Wang, J. (2025). Optimizing hybrid RIS-aided ISAC systems in V2X networks: A deep reinforcement learning method for anti-eavesdropping techniques. IEEE Transactions on Vehicular Technology, 74 (6), 9224-9239.
13. Yao, Y., Zhao, J., Li, Z., Cheng, X., & Wu, L. (2023). Jamming and eavesdropping defense scheme based on deep reinforcement learning in autonomous vehicle networks. IEEE Transactions on Information Forensics and Security, 18, 1211-1224.
14. Wang, Y., He, S., Chen, G., Chen, Y., & Jiang, D. (2022, December). XLM-D: Decorate cross-lingual pre-training model as non-autoregressive neural machine translation. In Proceedings of the 2022 conference on empirical methods in natural language processing (pp. 6934-6946).
15. 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.
16. 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.
17. Li, X., Wang, P., Li, G., & Zhang, Y. (2023). Design of a novel self-test-on-chip interface ASIC for capacitive accelerometers. IEEE Transactions on Circuits and Systems I: Regular Papers, 70(7), 2834-2843.
18. 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.
19. Wang, J., Malawade, A. V., Zhou, J., Yu, S. Y., & Al Faruque, M. A. (2024, January). Rs2g: Data-driven scene-graph extraction and embedding for robust autonomous perception and scenario understanding. In 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (pp. 7478-7487). IEEE.
20. Yang, Z., Ji, W., & Wang, Z. (2024). Adaptive joint configuration optimization for collaborative inference in edge-cloud systems. Science China Information Sciences, 67(4), 149103.
21. Chai, L., Zhang, J., Li, H., Cui, C., Jiang, J., Zheng, B., ... & Jiang, L. (2021). Investigation of thermomorphogenesis-related genes for a multi-silique trait in Brassica napus by comparative transcriptome analysis. Frontiers in Genetics, 12, 678804.
22. Jia, Y., Wang, T., Xiao, K., & Guo, C. (2020). How to reduce opportunism through contractual governance in the cross-cultural supply chain context: evidence from Chinese exporters. Industrial Marketing Management, 91, 323-337.
23. Zhang, Z., Zhang, Y., Zeng, A., Pan, D., Ji, Y., Zhang, Z., & Lin, J. (2023, September). Time-series data imputation via realistic masking-guided tri-attention bi-gru. In ECAI 2023: 26th European Conference on Artificial Intelligence (pp. 3074-3082).