IRMA
Interpretable and Robust Machine Learning for Mobility Analysis
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 often difficult to interpret and lack robustness, which slows the deployment of these AI-powered algorithms in practice. To improve their usability in deployment, an increasing research effort has been devoted to developing interpretable and robust machine learning methods, among which the causal inference approach recently gained traction as it can provide interpretable and actionable information. However, most methods are developed for image or sequential data which cannot satisfy the specific requirements of mobility data analysis. These unique requirements have been intensively studied in the Geographic Information Science (GIScience) field but have not yet been well utilized in developing machine learning models. The goal of our project is to bring together the knowledge of GIScience and Machine Learning, advancing our understanding of how interpretable and robust machine learning methods can be tailored to mobility analysis with the support of causal inference. The outcome of this research will deepen our understanding of how to integrate AI technologies and GIScience for mobility analysis, making AI in the transportation sector more interpretable and reliable. Ultimately, we aim to facilitate the deployment of AI in intelligent transportation systems and build a safer, more efficient, and more sustainable transportation system in the future.
People
Collaborators
Simon joined the SDSC as a senior data scientist in April 2022. He conducted his doctoral studies on statistical modeling of genetic data at ETH Zürich and obtained his MSc and BSc degrees at Technical University Munich in computer science. Before joining the SDSC, Simon worked as a freelance statistical consultant, and as an ML scientist at an AI startup in Lugano where he built experience in various topics ranging from generative modeling over Bayesian optimization to time series forecasting. Simon's research interests and expertise lie broadly in probabilistic machine and deep learning, causal inference, generative modeling, and their application in the natural sciences. Simon is an avid open-source software contributor and particularly enthusiastic about probabilistic programming languages, such as Stan.
Fernando Perez-Cruz received a PhD. in Electrical Engineering from the Technical University of Madrid. He is Titular Professor in the Computer Science Department at ETH Zurich and Head of Machine Learning Research and AI at Spiden. He has been a member of the technical staff at Bell Labs and a Machine Learning Research Scientist at Amazon. Fernando has been a visiting professor at Princeton University under a Marie Curie Fellowship and an associate professor at University Carlos III in Madrid. He held positions at the Gatsby Unit (London), Max Planck Institute for Biological Cybernetics (Tuebingen), and BioWulf Technologies (New York). Fernando Perez-Cruz has served as Chief Data Scientist at the SDSC from 2018 to 2023, and Deputy Executive Director of the SDSC from 2022 to 2023
PI | Partners:
ETH Zurich, Mobility Information Engineering Lab:
- Prof. Dr. Martin Raubal
- Dr. Yanan Xin
- Ye Hong
description
Motivation
Recent research on computational methods for mobility analysis has focused on black-box deep learning methods, because of their superior predictive power compared to conventional methods in many mobility-related applications. Despite their predictive performance, deep learning based algorithms typically have several shortcomings: a) they lack interpretability, b) they do generally not provide uncertainty estimates, c) it is unclear whether they are robust to distributional shifts in the input data, and d) they are typically not privacy preserving, i.e., the trained neural network weights can reflect confidential information, for instance, when trained on personal GPS tracking and location data.
Proposed Approach / Solution
For this project, we develop novel methods for enhancing the interpretability and robustness of machine learning models for mobility analysis. We first develop a benchmarking framework and datasets by simulating synthetic mobility data using both mechanistic models and generative AI models (Figure 1). The mechanistic models are designed to generate controlled interventional data for evaluating the robustness of neural networks (Hong et al., 2023). The generative denoising diffusion model is developed to simulate privacy-preserving mobility data (Dirmeier et al., 2024), since it does not rely on statistics of the data that might reveal information of individuals. Based on the simulated data, we assess how robust deep learning-based predictors are to distributional shifts in the input data and we present an approach that is able to discern in-distribution data from out-of-distribution data based on density estimation (Figure 2; Dirmeier et al., 2023). In addition, we present a data-driven approach to inform decision-making in mobility using counterfactual explanations (Figure 3; Wang et al., 2024).
Impact
The outcome of this research will deepen our understanding of how to integrate AI technologies and GIScience for mobility analysis, making AI in the transportation sector more interpretable and reliable. Ultimately, we aim to facilitate the deployment of AI in intelligent transportation systems, which could make the transportation system safer, more efficient, and more
sustainable in the future.
Presentation
Gallery
Annexe
Publications
- Hong, Y., Xin, Y., Dirmeier, S., Perez-Cruz, F., & Raubal, M. (2023). Revealing behavioral impact on mobility prediction networks through causal interventions. arXiv preprint arXiv:2311.11749.
doi:10.48550/arXiv.2311.11749 - Dirmeier, S., Hong, Y., Xin, Y., & Perez-Cruz, F. (2023). Uncertainty quantification and out-of-distribution detection using surjective normalizing flows. arXiv preprint arXiv:2311.00377.
doi:10.48550/arXiv.2311.00377 - Dirmeier, S., Hong, Y., & Perez-Cruz, F. (2024). Synthetic location trajectory generation using categorical diffusion models. arXiv preprint arXiv:2402.12242.
doi:10.48550/arXiv.2402.12242 - Wang, R., Xin, Y., Zhang, Y., Perez-Cruz, F., & Raubal, M. (2024). Counterfactual Explanations for Deep Learning-Based Traffic Forecasting. arXiv preprint arXiv:2405.00456.
doi:10.48550/arXiv.2405.00456
Additional resources
Bibliography
Publications
Related Pages
- GitHub organisation (including code for all case studies): Interpretable and robust machine learning for mobility analysis
More projects
ML-L3DNDT
BioDetect
FLBI
STIMO
News
Latest news
Smartair | An active learning algorithm for real-time acquisition and regression of flow field data
Smartair | An active learning algorithm for real-time acquisition and regression of flow field data
The Promise of AI in Pharmaceutical Manufacturing
The Promise of AI in Pharmaceutical Manufacturing
Efficient and scalable graph generation through iterative local expansion
Efficient and scalable graph generation through iterative local expansion
Contact us
Let’s talk Data Science
Do you need our services or expertise?
Contact us for your next Data Science project!