{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:39:00Z","timestamp":1760060340591,"version":"build-2065373602"},"reference-count":39,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T00:00:00Z","timestamp":1756252800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42171412"],"award-info":[{"award-number":["42171412"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>Traffic violations, the primary cause of road accidents, threaten public safety by disrupting traffic flow and causing substantial casualties and economic losses. Accurate spatiotemporal prediction of violations offers critical insights for proactive traffic management. While Graph Attention Network (GAT) methods excel in spatiotemporal forecasting, their practical deployment is hindered by prohibitive computational costs when handling dynamic large-scale data. To address this issue, we propose a Lightweight Traffic Violation Prediction with Graph Attention Distillation (LTVPGA) model, transferring spatial topology comprehension from a complex GAT to an efficient multilayer perceptron (MLP) via knowledge distillation. Our core contribution lies in topology-invariant knowledge transfer, where spatial relation priors distilled from the teacher\u2019s attention heads enable the MLP student to bypass explicit graph computation. This approach achieves significant efficiency gains for large-scale data\u2014notably accelerated inference time and reduced memory overhead\u2014while preserving modeling capability. We conducted a performance comparison between LTVPGA, Conv-LSTM, and GATR (teacher model). LTVPGA achieved revolutionary efficiency: consuming merely 15% memory and 0.6% training time of GATR while preserving nearly the same accuracy. This capacity enables practical deployment without sacrificing fidelity, providing a scalable solution for intelligent transportation governance.<\/jats:p>","DOI":"10.3390\/ijgi14090332","type":"journal-article","created":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T07:43:16Z","timestamp":1756366996000},"page":"332","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LTVPGA: Distilled Graph Attention for Lightweight Traffic Violation Prediction"],"prefix":"10.3390","volume":"14","author":[{"given":"Yingzhi","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Traffic Management Engineering, Zhejiang Police College, Hangzhou 310053, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuquan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang Key Laboratory of Geographic Information Science, Hangzhou 310058, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1475-8480","authenticated-orcid":false,"given":"Feng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang Key Laboratory of Geographic Information Science, Hangzhou 310058, China"},{"name":"School of Earth Sciences, Zhejiang University, Hangzhou 310058, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"10262","DOI":"10.1109\/TITS.2023.3305380","article-title":"Transportation 5.0: The DAO to Safe, Secure, and Sustainable Intelligent Transportation Systems","volume":"24","author":"Wang","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.aap.2013.05.004","article-title":"Risk factors associated with traffic violations and accident severity in China","volume":"59","author":"Zhang","year":"2013","journal-title":"Accid. Anal. Prev."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/j.aap.2008.12.014","article-title":"Kernel density estimation and K-means clustering to profile road accident hotspots","volume":"41","author":"Anderson","year":"2009","journal-title":"Accid. Anal. Prev."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1016\/j.aap.2006.10.012","article-title":"A crash-prediction model for multilane roads","volume":"39","author":"Caliendo","year":"2007","journal-title":"Accid. Anal. Prev."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1016\/j.trc.2015.03.015","article-title":"A novel variable selection method based on frequent pattern tree for real-time traffic accident risk prediction","volume":"55","author":"Lin","year":"2015","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Chen, Q., Song, X., Fan, Z., Xia, T., Yamada, H., and Shibasaki, R. (2018, January 10\u201312). A context-aware nonnegative matrix factorization framework for traffic accident risk estimation via heterogeneous data. Proceedings of the 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), Miami, FL, USA.","DOI":"10.1109\/MIPR.2018.00077"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Yu, R., and Liu, X.Q. (2010, January 22). Study on Traffic Accidents Prediction Model Based on RBF Neural Network. Proceedings of the International Conference on Information Engineering & Computer Science, Xi\u2019an, China.","DOI":"10.1109\/ICIECS.2010.5678126"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zeng, K.H., Chou, S.H., Chan, F.H., Niebles, J.C., and Sun, M. (2017, January 21\u201326). Agent-centric risk assessment: Accident anticipation and risky region localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Hawaii, HI, USA.","DOI":"10.1109\/CVPR.2017.146"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Xiao, T., Lu, H., Wang, J., and Wang, K. (2021). Predicting and interpreting spatial accidents through MDLSTM. Int. J. Environ. Res. Public Health, 18.","DOI":"10.3390\/ijerph18041430"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Najjar, A., Kaneko, S.I., and Miyanaga, Y. (2017, January 4\u20139). Combining satellite imagery and open data to map road safety. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.","DOI":"10.1609\/aaai.v31i1.11168"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"105371","DOI":"10.1016\/j.aap.2019.105371","article-title":"Real-time crash risk prediction on arterials based on LSTM-CNN","volume":"135","author":"Li","year":"2019","journal-title":"Accid. Anal. Prev."},{"key":"ref_12","first-page":"1613","article-title":"Traffic accident quantity prediction model based on dual-scale long short-term memory network","volume":"54","author":"Li","year":"2020","journal-title":"J. Zhejiang Univ. (Eng. Sci.)"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Zhou, X., and Yang, T. (2018, January 19\u201323). Hetero-convlstm: A deep learning approach to traffic accident prediction on heterogeneous spatio-temporal data. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, New York, NY, USA.","DOI":"10.1145\/3219819.3219922"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zheng, H., Feng, X., and Chen, Z. (2017, January 11\u201313). Short-term traffic flow prediction with Conv-LSTM. Proceedings of the 2017 9th International Conference on Wireless Communications and Signal Processing (WCSP), Nanjing, China.","DOI":"10.1109\/WCSP.2017.8171119"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Yu, B., Yin, H., and Zhu, Z. (2018, January 13\u201319). Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI), Stockholm, Sweden.","DOI":"10.24963\/ijcai.2018\/505"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref_17","first-page":"4189","article-title":"Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting","volume":"35","author":"Li","year":"2021","journal-title":"AAAI Tech. Track Data Min. Knowl. Manag."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3848","DOI":"10.1109\/TITS.2019.2935152","article-title":"T-GCN: A Temporal Graph Convolutional. Network for Traffic Prediction","volume":"21","author":"Zhao","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"17654","DOI":"10.1109\/TITS.2022.3155749","article-title":"Graph-based spatial-temporal convolutional network for vehicle trajectory prediction in autonomous driving","volume":"23","author":"Sheng","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_20","first-page":"2239377","article-title":"Graph convolutional networks with learnable spatial weightings for traffic forecasting applications","volume":"21","author":"Chen","year":"2025","journal-title":"Transp. A Transp. Sci."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1049\/itr2.12254","article-title":"A multi-attention dynamic graph convolution network with cost-sensitive learning approach to road-level and minute-level traffic accident prediction","volume":"17","author":"Wu","year":"2023","journal-title":"IET Intell. Transp. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3596603","article-title":"TAP: Traffic Accident Profiling via Multi-Task Spatio-Temporal Graph Representation Learning","volume":"17","author":"Liu","year":"2023","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"ref_23","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., and Bengio, Y. (May, January 30). Graph attention networks. Proceedings of the 6th International Conference on Learning Representations (ICLR), Vancouver, BC, Canada."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Bai, J., Zhu, J., Song, Y., Zhao, L., Hou, Z., Du, R., and Li, H. (2021). A3T-GCN: Attention Temporal Graph Convolutional Network for Traffic Forecasting. ISPRS Int. J. Geo-Inf., 10.","DOI":"10.3390\/ijgi10070485"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Wang, Y., Zhang, F., Zhou, H., Sun, K., and Yu, Y. (2023). GATR: A Road Network Traffic Violation Prediction Method Based on Graph Attention Network. Int. J. Environ. Res. Public Health, 20.","DOI":"10.3390\/ijerph20043432"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2807","DOI":"10.1080\/09540091.2022.2151977","article-title":"Structural reinforcement-based graph convolutional networks","volume":"34","author":"Qin","year":"2022","journal-title":"Connect. Sci."},{"key":"ref_27","unstructured":"You, J., Ying, Z., and Leskovec, J. (March, January 27). Optimizing memory efficiency for graph convolutional networks on edge computing platforms. Proceedings of the 2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA), Seoul, Republic of Korea."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TITS.2005.845574","article-title":"Knowledge Generation and Distillation for Road Segmentation in Intelligent Transportation Systems","volume":"6","author":"Wang","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"92365","DOI":"10.1109\/ACCESS.2025.3573181","article-title":"Prune and Distill: A Novel Knowledge Distillation Method for GCNs-Based Recommender Systems","volume":"13","author":"Yi","year":"2025","journal-title":"IEEE Access"},{"key":"ref_31","unstructured":"Joshi, C., Liu, F., Xun, X., Lin, J., and Sheng, C. (2021). On Representation Knowledge Distillation for Graph Neural Networks. arXiv."},{"key":"ref_32","unstructured":"Zhang, S., Liu, Y., Sun, Y., and Shah, N. (2022, January 25\u201329). Graph-less neural networks: Teaching old mlps new tricks via distillation. Proceedings of the Tenth International Conference on Learning Representations, Virtual Event."},{"key":"ref_33","unstructured":"Hu, Y., You, H., Wang, Z., Zhou, E., and Gao, Y. (2021). Graph-MLP: Node classification without message passing in graph. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Izadi, M., Safayani, M., and Mirzaei, A. (2024). Knowledge Distillation on Spatial-Temporal Graph Convolutional Network for Traffic Prediction. arXiv.","DOI":"10.1080\/1206212X.2024.2442699"},{"key":"ref_35","first-page":"4695","article-title":"Distilled Neural Networks for Efficient Learning to Rank","volume":"35","author":"Franco","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge Distillation: A Survey","volume":"129","author":"Gou","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"ref_37","unstructured":"Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the Knowledge in a Neural Network. arXiv."},{"key":"ref_38","unstructured":"Hugo, T., Matthieu, C., Matthijs, D., Francisco, M., Alexandre, S., and Herv\u00e9, J. (2021). Training data-efficient image transformers & distillation through attention. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1038\/s41586-025-09005-y","article-title":"A foundation model for the Earth system","volume":"641","author":"Bodnar","year":"2025","journal-title":"Nature"}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/14\/9\/332\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:33:56Z","timestamp":1760034836000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/14\/9\/332"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"references-count":39,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["ijgi14090332"],"URL":"https:\/\/doi.org\/10.3390\/ijgi14090332","relation":{},"ISSN":["2220-9964"],"issn-type":[{"type":"electronic","value":"2220-9964"}],"subject":[],"published":{"date-parts":[[2025,8,27]]}}}