Abstract
Recently, micro-learning has been successfully applied to various scenarios, such as graph optimization (e.g. power grid management). In these approaches, ad-hoc models of local data are built instead of one large model on the overall data set. Micro-learning is typically useful for incremental, what-if/prospective scenarios, where one has to perform step-by-step decisions based on local properties. A common feature of these applications is that the predicted properties (such as speed of a bus line) are compositions of smaller parts (e.g. the speed on each bus inter-stations along the line). But little is known about the quality of such predictions when generalized at a larger scale.
In this paper we propose a generic technique that embeds machine-learning for graph-based compositional prediction, that allows 1) the prediction of the behaviour of composite objects, based on the predictions of their sub-parts and appropriate composition rules, and 2) the production of rich prospective analytics scenarios, where new objects never observed before can be predicted based on their simpler parts. We show that the quality of such predictions compete with macro-learning ones, while enabling prospective scenarios. We assess our work on a real size, operational bus network data set.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
Rennes transportation network: https://data.rennesmetropole.fr.
- 3.
Data and more material is available at https://gitlab.inria.fr/glyan/compred.
- 4.
More material about the bus lines is available in the README of the repository.
- 5.
More information about training data in the repository.
- 6.
More material is available in the public deposit.
References
Altinkaya, M., Zontul, M.: Urban bus arrival time prediction: a review of computational models. IJRTE 2, 164–169 (2013)
Amirat, H., Lagraa, N., Fournier-Viger, P., Ouinten, Y.: MyRoute: a graph-dependency based model for real-time route prediction. JCM 12, 668 (2017)
Barceló, J., Casas, J., GarcÃa, D., Perarnau, J.: Methodological Notes on Combining Macro, Meso and Micro Simulation Models for Transportation Analysis. In: Workshop on Modeling and Simulation. Sedona, AZ (2005)
Berger-Wolf, T., Chawla, N. (eds.): Proceedings of the 2019 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics, Philadelphia, PA, May 2019. https://doi.org/10.1137/1.9781611975673
Burghout, W., Koutsopoulos, H., Andréasson, I.: Hybrid mesoscopic-microscopic traffic simulation. Transp. Res. Rec. J. Transp. Res. Board 1934, 218–25 (2005)
Cerqueira, V., Torgo, L., Pinto, F., Soares, C.: Arbitrated ensemble for time series forecasting. In: Ceci, M., Hollmén, J., Todorovski, L., Vens, C., Džeroski, S. (eds.) ECML PKDD 2017. LNCS (LNAI), vol. 10535, pp. 478–494. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-71246-8_29
Cortés, C.E., Gibson, J., Gschwender, A., Munizaga, M., Zúñiga, M.: Commercial bus speed diagnosis based on GPS-monitored data. Transp. Res. Part C Emerg. Technol. 19(4), 695–707 (2011). https://doi.org/10.1016/j.trc.2010.12.008
Courtois, X., Dobruszkes, F.: L’(in)efficacité des trams et bus á Bruxelles, une analyse désagrégée. Brussels Studies. La revue scientifique électronique pour les recherches sur Bruxelles / Het elektronisch wetenschappelijk tijdschrift voor onderzoek over Brussel / The e-journal for academic research on Brussels (2008). https://doi.org/10.4000/brussels.603
Fernandez, R., Valenzuela, E.: A model to predict bus commercial speed. Traffic Eng. Control 44(2) (2003)
Fu, C., et al.: Link weight prediction using supervised learning methods and its application to yelp layered network. IEEE Trans. Knowl. Data Eng. 30(8), 1507–1518 (2018). https://doi.org/10.1109/TKDE.2018.2801854
Hou, Y., Holder, L.B.: On graph mining with deep learning: introducing model R for link weight prediction. J. Artif. Intell. Soft Comput. Res. 9(1), 21–40 (2019). https://doi.org/10.2478/jaiscr-2018-0022
Kumar, S., Spezzano, F., Subrahmanian, V.S., Faloutsos, C.: Edge weight prediction in weighted signed networks. In: 2016 IEEE 16th International Conference on Data Mining (ICDM), Barcelona, Spain, pp. 221–230. IEEE, December 2016. https://doi.org/10.1109/ICDM.2016.0033
Ma, X., Chen, X.: Public transportation big data mining and analysis. In: Data-Driven Solutions to Transportation Problems. Elsevier (2019)
Matsumoto, T., Sakakibara, K., Tamaki, H.: Bus line optimization using multi-agent simulation model of urban traffic behavior of inhabitants applying branch and bound techniques, pp. 234–239. IEEE, July 2015. https://doi.org/10.1109/SICE.2015.7285551
Mendes-Moreira, J., Baratchi, M.: Reconciling predictions in the regression setting: an application to bus travel time prediction. In: Berthold, M.R., Feelders, A., Krempl, G. (eds.) IDA 2020. LNCS, vol. 12080, pp. 313–325. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-44584-3_25
Petersen, N.C., Rodrigues, F., Pereira, F.C.: Multi-output bus travel time prediction with convolutional LSTM neural network. Expert Syst. Appl. 120, 426–435 (2019)
Pontius, R.G., Thontteh, O., Chen, H.: Components of information for multiple resolution comparison between maps that share a real variable. Environ. Ecol. Stat. 15(2), 111–142 (2008). https://doi.org/10.1007/s10651-007-0043-y
Robinson, S., Narayanan, B., Toh, N., Pereira, F.: Methods for pre-processing smartcard data to improve data quality. Transp. Res. Part C Emerg. Technol. 49, 43–58 (2014). https://doi.org/10.1016/j.trc.2014.10.006
Hartmann, T., Moawad, A., Fouquet, F., Le Traon, Y.: The next evolution of MDE: a seamless integration of machine learning into domain modeling. SoSyM 18, 1285–1304 (2017)
Taskar, B., Wong, M.F., Abbeel, P., Koller, D.: Link prediction in relational data. Adv. Neural Inf. Process. Syst. 16, 659–666 (2003)
Thomas, H., Fouquet, F., Moawad, A., Rouvoy, R., Traon, Y.L.: GreyCat: efficient what-if analytics for data in motion at scale. IS 83, 101–117 (2019)
Treethidtaphat, W., Pattara-Atikom, W., Khaimook, S.: Bus arrival time prediction at any distance of bus route using deep neural network model. In: International Conference On Intelligent Transportation (2017)
Zaki, M., Ashour, I., Zorkany, M., Hesham, B.: Online bus arrival time prediction using hybrid neural network and Kalman filter techniques. IJMER 3, 2035–2041 (2013)
Zhang, H., Liang, S., Han, Y., Ma, M., Leng, R.: A prediction model for bus arrival time at bus stop considering signal control and surrounding traffic flow. IEEE Access 8, 127672–127681 (2020)
Zhao, J., et al.: Prediction of links and weights in networks by reliable routes. Sci. Rep. 5(1), 12261 (2015). https://doi.org/10.1038/srep12261
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Lyan, G., Amblard, D.G., Jezequel, JM. (2021). On the Quality of Compositional Prediction for Prospective Analytics on Graphs. In: Kotsis, G., et al. Database and Expert Systems Applications - DEXA 2021 Workshops. DEXA 2021. Communications in Computer and Information Science, vol 1479. Springer, Cham. https://doi.org/10.1007/978-3-030-87101-7_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-87101-7_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87100-0
Online ISBN: 978-3-030-87101-7
eBook Packages: Computer ScienceComputer Science (R0)