Metadata Driven Modeling of Green Finance Transmission Paths Influencing Economic Growth in Ethnic Mountainous Regions
Main Article Content
Abstract
To address the challenges of aligning heterogeneous data from multiple sources in ethnic minority mountainous areas and the difficulty in identifying the nonlinear time-delay structure of green finance transmission paths, this paper first constructs a heterogeneous graph containing five types of nodes and three types of edges using metadata. Then, a dynamic graph variational encoder is used to output the latent variables of candidate paths. Finally, a gated cyclic decoder is used to simulate the time-delay transmission and attenuation of funds, jointly optimizing prediction error, path sparsity regularization, and causal prior constraints. Experiments identified six core transmission paths with a prediction determination coefficient of 0.865, and all path coefficients in the posterior interval did not contain zeros. The results demonstrate that the metadata-driven graph variational autoencoder can discover interpretable transmission paths end-to-end, providing a quantitative basis for green finance policies in ethnic minority mountainous areas.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
R. De Haas and A. Popov, “Finance and Green Growth,” The Economic Journal, vol. 133, no. 650, pp. 637–668, 2023, doi: 10.1093/ej/ueac081.
K. H. Wang, Y. X. Zhao, C. F. Jiang, and Z. Z. Li, “Does green finance inspire sustainable development? Evidence from a global perspective,” Economic Analysis and Policy, vol. 75, pp. 412–426, 2022, doi: 10.1016/j.eap.2022.06.002.
J. Gao, D. Wu, Q. Xiao, A. A. Randhawa, Q. Liu, and T. Zhang, “Green finance, environmental pollution and high-quality economic development— a study based on China’s provincial panel data,” Environmental Science and Pollution Research, vol. 30, no. 11, pp. 31954–31976, 2023, doi: 10.1007/s11356-022-24428-0.
J. Wang, S. Zhang, Y. Xiao, and R. Song, “A Review on Graph Neural Network Methods in Financial Applications,” Journal of Data Science, vol. 20, no. 2, pp. 111–134, 2022, doi: 10.6339/22-JDS1047.
S. Bloemheuvel, J. van den Hoogen, D. Jozinovi´c, A. Michelini, and M. Atzmueller, “Graph neural networks for multivariate time series regression with application to seismic data,” International Journal of Data Science and Analytics, vol. 16, no. 3, pp. 317–332, 2023, doi: 10.1007/s41060-022-00349-6.
M. Jin, H. Y. Koh, Q. Wen, D. Zambon, C. Alippi, G. I. Webb, I. King, and S. Pan, “A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 12, pp. 10466– 10485, 2024, doi: 10.1109/TPAMI.2024.3443141.
Y. Wang, “Advances in spatiotemporal graph neural network prediction research,” International Journal of Digital Earth, vol. 16, no. 1, pp. 2034– 2066, 2023, doi: 10.1080/17538947.2023.2220610.
Z. Ye, Y. J. Kumar, G. O. Sing, F. Song, and J. Wang, “A Comprehensive Survey of Graph Neural Networks for Knowledge Graphs,” IEEE Access, vol. 10, no. 1, pp. 75729–75741, 2022, doi: 10.1109/ACCESS.2022.3191784.
M. Masmoudi, S. Ben Abdallah Ben Lamine, M. H. Karray, et al., “Semantic data integration and querying: A survey and challenges,” ACM Computing Surveys, vol. 56, no. 8, pp. 1–35, 2024, doi: 10.1145/3653317.
L. Zhong, J. Wu, Q. Li, et al., “A comprehensive survey on automatic knowledge graph construction,” ACM Computing Surveys, vol. 56, no. 4, pp. 1–62, 2023, doi: 10.1145/3618295.
M. Hofer, D. Obraczka, A. Saeedi, H. Köpcke, and E. Rahm, “Construction of Knowledge Graphs: Current State and Challenges,” Information, vol. 15, no. 8, pp. 509–517, 2024, doi: 10.3390/info15080509.
R. Bing, G. Yuan, M. Zhu, F. Meng, H. Ma, and S. Qiao, “Heterogeneous graph neural networks analysis: a survey of techniques, evaluations and applications,” Artificial Intelligence Review, vol. 56, no. 8, pp. 8003–8042, 2023, doi: 10.1007/s10462-022-10375-2.
N. Mrabah, M. Bouguessa, M. F. Touati, and R. Ksantini, “Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering,” IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 9, pp. 9037–9053, 2023, doi: 10.1109/TKDE.2022.3220948.