Abstract
The objective of cross-city transfer learning methods focuses on how to effectively transfer knowledge from data-rich cities to help data-scarce cities, and solve the problem that city development levels are quite unbalanced. However, transfer-learning and meta-learning-based spatial-temporal approaches can quickly learn and adapt to (novel-) source cities, but the prior experience in base-source cities will be largely forgotten, i.e., the models may lead to catastrophic forgetting problem on base attributes. In this paper, we proposed an incremental few-shot learning based spatial-temporal model (IFS-STP), which utilized an incremental few-shot learner strives to build a generalized model that can not only transfer learned knowledge from source cities to improve the performance of spatial-temporal prediction in a target city with limited data but also prevent the catastrophic forgetting problem of source cities. We evaluate IFS-STP on traffic prediction tasks and the experience results show that our approach significantly outperforms competitive baseline models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Liu, Y., Zhao, K., Cong, G.: Efficient similar region search with deep metric learning. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1850–1859 (2018)
Wei, H., Zheng, G., Yao, H., Li, Z.: Intellilight: A reinforcement learning approach for intelligent traffic light control. In: The 24th ACM SIGKDD, pp. 2496–2505 (2018)
Lippi, M., Bertini, M., Frasconi, P.: Short-term traffic flow forecasting: an experimental comparison of time-series analysis and supervised learning. IEEE Trans. Intell. Trans. Syst. 14(2), 871–882 (2013)
Moreira-Matias, L., Gama, J., Ferreira, M., Mendes-Moreira, J., Damas, L.: Predicting taxi–passenger demand using streaming data. IEEE Trans. Intell. Trans. Syst. 14(3), 1393–1402 (2013)
Zheng, J., Ni, L.M.: Time-dependent trajectory regression on road networks via multi-task learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, 27(1), (2013)
Yi, X., Zhang, J., Wang, Z., Li, T., Zheng, Y.: Deep distributed fusion network for air quality prediction. In: Proceedings of the 24th ACM SIGKDD, pp. 965–973 (2018)
Yao, H., et al.: Deep multi-view spatial-temporal network for taxi demand prediction, In: AAAI, vol. 32(1), pp. 2588–2595 (2018)
Zhang, J., Zheng, Y., Qi, D.: Deep spatio-temporal residual networks for citywide crowd flows prediction. In: Thirty-first AAAI Conference, vol. 31(1), pp. 1655–1661 (2017)
Yao, H., Liu, Y., Wei, Y., Tang, X., Li, Z.: Learning from multiple cities: a meta-learning approach for spatial-temporal prediction. In: WWW Conference, pp. 2181–2191 (2019)
Pan, S.J., Tsang, I.W., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Networks 22(2), 199–210 (2011)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, pp. 1126–1135 (2017)
Goodfellow, I.J., Mirza, M., Courville, A., Bengio, Y.: An empirical investigation of catastrophic forgetting in gradient-based neural networks. Stat. 6, 1050 (2014)
Wang, L., Geng, X., Ma, X., Liu, F., Yang, Q.: Cross-city transfer learning for deep spatio-temporal prediction. In: Proceedings of the 28th IJCAI, pp. 1893–1899 (2019)
Wang, H., Yao, H., Kifer, D., Graif, C., Li, Z.: Non-Stationary model for crime rate inference using modern urban data. IEEE Trans, Big Data 5(2), 180–194 (2017)
Fei, W., Wang, H., Li, Z.: Interpreting traffic dynamics using ubiquitous urban data. In: Proceedings of the 24th ACM SIGSPATIAL, pp.1–4 (2016)
Tong, Y., Chen, Y., Zhou, Z., Lei, C., Lv, W.: The simpler the better: a unified approach to predicting original taxi demands based on large-scale online platforms. In: ACM SIGKDD, pp. 1653–1662 (2017)
Rose, Y., Li, Y., Shahabi, C., Demiryurek, U., Liu, Y.: Deep learning: a generic approach for extreme condition traffic forecasting. In: Chawla, N., Wang, W. (eds.) Proceedings of the 2017 SIAM International Conference on Data Mining, pp. 777–785. Society for industrial and applied mathematics, Philadelphia, PA (2017). https://doi.org/10.1137/1.9781611974973.87
Yao, H., et al.: Deep multi-view spatial-temporal network for taxi demand prediction. In: Proceedings of the AAAI, 32 (1) (2018)
Sun, Q., Liu, Y., Chua, T.S., Schiele, B.: Meta-transfer learning for few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 403–412 (2019)
Jiang, W., Huang, K., Geng, J., Deng, X.: Multi-Scale metric learning for few-shot learning. IEEE Trans, Circuits Syst. Video Technol. 31(3), 1091–1102 (2021)
Ren, M., Liao, R., Fetaya, E., Zemel, R.: Incremental few-shot learning with attention attractor networks. Adv. NeurIPS 32, 5275–5285 (2019)
Wei, Y., Zheng, Y., Yang, Q.: Transfer knowledge between cities. In: Proceedings of the 22nd ACM SIGKDD, pp. 1905–1914 (2016)
Yao, H., Tang, X., Wei, H., Zheng, G.: mRevisiting spatial-temporal similarity: a deep learning framework for traffic prediction, In: The 33rd AAAI Conference, pp. 5668–5675 (2019)
Shi, X., Chen, Z., Wang, H., Yeung, D., Wong, W.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: NeurIPS, pp. 802–810 (2015)
Yoon, S.W., Kim, D.Y., Seo, J., Moon, J.: Xtarnet: Learning to extract task-adaptive representation for incremental few-shot learning. In: ICML, pp. 10852–10860 (2020)
Xiang, L., Jin, X., Ding, G., Han, J., Li, L.: Incremental few-shot learning for pedestrian attribute recognition, In Proceedings of the 28th IJCAI 2019, pp. 3912–3918 (2019)
LIU, L., Zhou, T., Long, G., Jiang, J., Zhang, C.: Learning to Propagate for Graph Meta-Learning. In: Advances in Neural Information Processing Systems, 32, 1039–1050 (2019)
Liao, R., et al.: Reviving and improving recurrent back-propagation. In Proceedings of the 35th ICML 2018, Stockholmsmassan, Stockholm, Sweden, pp. 3088–3097 (2018)
Pineda, F.J.: Generalization of back propagation to recurrent and higher order neural networks. In: Anderson, D.Z., (ed.) Neural Information Processing Systems, Denver, Colorado, USA, American Institue of Physics, pp. 602–611 (1987)
Hyndman, R.J., Athanasopoulos, G. Forecasting: principles and practice. OTexts (2018)
Wang, L., Geng, X., Ma, X., Liu, F., Yang, Q.: Crowd flow prediction by deep spatio-temporal transfer learning. arXiv preprint arXiv:1802.00386 (2018)
Williams, R.J., Peng, J.: An efficient gradient-based algorithm for on-line training of recurrent network trajectories. Neural Comput. 2(4), 490–501 (1990)
Sprechmann, P., Jayakumar, S.M., Rae, J.W., Pritzel.: Memory-based parameter adaptation. In: The 6th International Conference on Learning Representations, ICLR (2018)
Acknowledgement
This work is supported by UESTC-ZHIXIAOJING Joint Research Center of Smart Home (No. H04W210180), Neijiang technology incubation and transformation Funds (No. 2021KJFH004).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Wang, J., Li, W., Qi, X., Ren, Y. (2021). Transfer Knowledge Between Cities by Incremental Few-Shot Learning. In: Gao, H., Wang, X. (eds) Collaborative Computing: Networking, Applications and Worksharing. CollaborateCom 2021. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 407. Springer, Cham. https://doi.org/10.1007/978-3-030-92638-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-92638-0_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92637-3
Online ISBN: 978-3-030-92638-0
eBook Packages: Computer ScienceComputer Science (R0)