ABSTRACT
Artificial intelligence (AI) is revolutionizing many areas of our lives, leading a new era of technological advancement. Particularly, the transportation sector would benefit from the progress in AI and advance the development of intelligent transportation systems. Building intelligent transportation systems requires an intricate combination of artificial intelligence and mobility analysis. The past few years have seen rapid development in transportation applications using advanced deep neural networks. However, such deep neural networks are difficult to interpret and lack robustness, which slows the deployment of these AI-powered algorithms in practice. To improve their usability, increasing research efforts have been devoted to developing interpretable and robust machine learning methods, among which the causal inference approach recently gained traction as it provides interpretable and actionable information. Moreover, most of these methods are developed for image or sequential data which do not satisfy specific requirements of mobility data analysis. This vision paper emphasizes research challenges in deep learning-based mobility analysis that require interpretability and robustness, summarizes recent developments in using causal inference for improving the interpretability and robustness of machine learning methods, and highlights opportunities in developing causally-enabled machine learning models tailored for mobility analysis. This research direction will make AI in the transportation sector more interpretable and reliable, thus contributing to safer, more efficient, and more sustainable future transportation systems.
- Kartik Ahuja, Karthikeyan Shanmugam, Kush Varshney, and Amit Dhurandhar. 2020. Invariant risk minimization games. In International Conference on Machine Learning. PMLR, 145--155.Google Scholar
- Kamal Akbari, Stephan Winter, and Martin Tomko. 2021. Spatial Causality: A Systematic Review on Spatial Causal Inference. Geographical Analysis (2021).Google Scholar
- Gennady Andrienko, Natalia Andrienko, and Marco Heurich. 2011. An event-based conceptual model for context-aware movement analysis. International Journal of Geographical Information Science 25, 9 (2011), 1347--1370.Google ScholarDigital Library
- Martin Arjovsky, Léon Bottou, Ishaan Gulrajani, and David Lopez-Paz. 2019. Invariant risk minimization. arXiv preprint arXiv:1907.02893 (2019).Google Scholar
- Oliver Burkhard, Henrik Becker, Robert Weibel, and Kay W Axhausen. 2020. On the requirements on spatial accuracy and sampling rate for transport mode detection in view of a shift to passive signalling data. Transportation Research Part C: Emerging Technologies 114 (2020), 99--117.Google ScholarCross Ref
- Peter Bühlmann and others. 2020. Invariance, causality and robustness. Statist. Sci. 35, 3 (2020), 404--426. Publisher: Institute of Mathematical Statistics.Google Scholar
- Diogo V Carvalho, Eduardo M Pereira, and Jaime S Cardoso. 2019. Machine learning interpretability: A survey on methods and metrics. Electronics 8, 8 (2019), 832.Google ScholarCross Ref
- European Commission, Content Directorate-General for Communications Networks, and Technology. 2019. Ethics guidelines for trustworthy AI. Publications Office. Google ScholarCross Ref
- David H Douglas and Thomas K Peucker. 1973. Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. Cartographica: the international journal for geographic information and geovisualization 10, 2 (1973), 112--122.Google Scholar
- Jean Dubé, Diègo Legros, Marius Thériault, and François Des Rosiers. 2014. A spatial difference-in-differences estimator to evaluate the effect of change in public mass transit systems on house prices. Transportation Research Part B: Methodological 64 (2014), 24--40.Google ScholarCross Ref
- Alireza Ermagun and David Levinson. 2018. Spatiotemporal traffic forecasting: review and proposed directions. Transport Reviews 38, 6 (2018), 786--814.Google ScholarCross Ref
- Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, and Victor Lempitsky. 2016. Domain-adversarial training of neural networks. The journal of machine learning research 17, 1 (2016), 2096--2030. Publisher: JMLR. org.Google Scholar
- Christina Heinze-Deml, Jonas Peters, and Nicolai Meinshausen. 2018. Invariant causal prediction for nonlinear models. Journal of Causal Inference 6, 2 (2018). Publisher: De Gruyter.Google Scholar
- Amruta Khot, Abdeltawab Hendawi, Anderson Nascimento, Raj Katti, Ankur Teredesai, and Mohamed Ali. 2014. Road network compression techniques in spatiotemporal embedded systems: A survey. In Proceedings of the 5th ACM SIGSPATIAL International Workshop on GeoStreaming. 33--36.Google ScholarDigital Library
- Nishant Kumar and Martin Raubal. 2021. Applications of deep learning in congestion detection, prediction and alleviation: A survey. Transportation Research Part C: Emerging Technologies 133 (2021), 103432.Google ScholarCross Ref
- Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. In NeurIPS.Google Scholar
- Ibai Laña, Javier J Sanchez-Medina, Eleni I Vlahogianni, and Javier Del Ser. 2021. From data to actions in intelligent transportation systems: A prescription of functional requirements for model actionability. Sensors 21, 4 (2021), 1121.Google ScholarCross Ref
- Yuejiang Liu, Riccardo Cadei, Jonas Schweizer, Sherwin Bahmani, and Alexandre Alahi. 2022. Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 17081--17092.Google ScholarCross Ref
- Massimiliano Luca, Gianni Barlacchi, Bruno Lepri, and Luca Pappalardo. 2021. A survey on deep learning for human mobility. ACM Computing Surveys (CSUR) 55, 1 (2021), 1--44.Google ScholarDigital Library
- Daniel McDuff, Yale Song, Jiyoung Lee, Vibhav Vineet, Sai Vemprala, Nicholas Alexander Gyde, Hadi Salman, Shuang Ma, Kwanghoon Sohn, and Ashish Kapoor. 2022. Causalcity: Complex simulations with agency for causal discovery and reasoning. In Conference on Causal Learning and Reasoning. PMLR, 559--575.Google Scholar
- Konrad P Mielke, Tom Claassen, J Huijbregts, Aafke M Schipper, and Tom M Heskes. 2020. Discovering cause-effect relationships in spatial systems with a known direction based on observational data. In International Conference on Probabilistic Graphical Models. PMLR, 305--316.Google Scholar
- Christoph Molnar. 2020. Interpretable machine learning. Lulu. com.Google Scholar
- Joris M Mooij, Jonas Peters, Dominik Janzing, Jakob Zscheischler, and Bernhard Schölkopf. 2016. Distinguishing cause from effect using observational data: methods and benchmarks. Journal of Machine Learning Research 17 (2016), 1--102.Google ScholarDigital Library
- Tuhin Paul, Kevin Stanley, Nathaniel Osgood, Scott Bell, and Nazeem Muhajarine. 2016. Scaling behavior of human mobility distributions. In The Annual International Conference on Geographic Information Science. Springer, 145--159.Google ScholarCross Ref
- Judea Pearl. 1988. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann Series in Representation and Reasoning.Google Scholar
- Judea. Pearl. 2009. Causality. Cambridge University Press.Google Scholar
- Judea Pearl. 2019. The seven tools of causal inference, with reflections on machine learning. Commun. ACM 62, 3 (2019), 54--60.Google ScholarDigital Library
- Jonas Peters, Peter Bühlmann, and Nicolai Meinshausen. 2016. Causal inference by using invariant prediction: identification and confidence intervals. Journal of the Royal Statistical Society. Series B: Statistical Methodology 78, 5 (2016), 947--1012.Google ScholarCross Ref
- Jonas Peters, Dominik Janzing, and Bernhard Schölkopf. 2017. Elements of Causal Inference: Foundations and Learning Algorithms. MIT Press (available on-line).Google ScholarDigital Library
- Weicheng Qian, Kevin G Stanley, and Nathaniel D Osgood. 2013. The impact of spatial resolution and representation on human mobility predictability. In International Symposium on Web and Wireless Geographical Information Systems. Springer, 25--40.Google ScholarDigital Library
- Martin Raubal. 2020. Spatial data science for sustainable mobility. Journal of Spatial Information Science 20 (2020), 109--114.Google Scholar
- Kai-Florian Richter, Falko Schmid, and Patrick Laube. 2012. Semantic trajectory compression: Representing urban movement in a nutshell. Journal of Spatial Information Science 4 (2012), 3--30.Google Scholar
- Mateo Rojas-Carulla, Bernhard Schölkopf, Richard Turner, and Jonas Peters. 2018. Invariant models for causal transfer learning. The Journal of Machine Learning Research 19, 1 (2018), 1309--1342. Publisher: JMLR. org.Google ScholarDigital Library
- Thomas Rojat, Raphaël Puget, David Filliat, Javier Del Ser, Rodolphe Gelin, and Natalia Díaz-Rodríguez. 2021. Explainable artificial intelligence (xai) on timeseries data: A survey. arXiv preprint arXiv:2104.00950 (2021).Google Scholar
- Bernhard Schölkopf. 2019. Causality for Machine Learning. arXiv preprint arXiv:1911.10500 (2019).Google Scholar
- Natasa Tagasovska and David Lopez-Paz. 2019. Single-Model Uncertainties for Deep Learning. In NeurIPS.Google Scholar
- Matthew Veres and Medhat Moussa. 2019. Deep learning for intelligent transportation systems: A survey of emerging trends. IEEE Transactions on Intelligent transportation systems 21, 8 (2019), 3152--3168.Google ScholarCross Ref
- Sandra Wachter, Brent Mittelstadt, and Chris Russell. 2018. Counterfactual explanations without opening the black box: Automated decisions and the GDPR. Harv. JL & Tech. 31 (2018), 841. Publisher: HeinOnline.Google Scholar
- Kui Yu, Xianjie Guo, Lin Liu, Jiuyong Li, Hao Wang, Zhaolong Ling, and Xindong Wu. 2020. Causality-based feature selection: Methods and evaluations. ACM Computing Surveys (CSUR) 53, 5 (2020), 1--36.Google ScholarDigital Library
Index Terms
- Vision paper: causal inference for interpretable and robust machine learning in mobility analysis
Recommendations
Density-based reliable and robust explainer for counterfactual explanation
AbstractAs an essential post-hoc explanatory method, counterfactual explanation enables people to understand and react to machine learning models. Works on counterfactual explanation generally aim at generating high-quality results, which means providing ...
A new approach based on association rules to add explainability to time series forecasting models
AbstractMachine learning and deep learning have become the most useful and powerful tools in the last years to mine information from large datasets. Despite the successful application to many research fields, it is widely known that some of these ...
Highlights- Novel methodology focused on visual explainability for time series forecasting.
- Use of association rules as an agnostic approach for adding explainability.
- Visual representation of the rules for a better interpretation of the ...
Scientific Exploration and Explainable Artificial Intelligence
AbstractModels developed using machine learning are increasingly prevalent in scientific research. At the same time, these models are notoriously opaque. Explainable AI aims to mitigate the impact of opacity by rendering opaque models transparent. More ...
Comments