Search for: All records

Abstract The COVID-19 pandemic and the resulting economic recession negatively affected many people’s physical, social, and psychological health and has been shown to change population-level mobility, but little attention has been given to park visitations as an indicator. Estimating the frequency of park visitations from aggregated mobility data of all the parks in Washington State (USA), we study trends in park use one year prior to and two years during the COVID-19 pandemic. Our findings indicate that the gravity model is a robust model for the park visitation behavior in different spatial resolutions of city level and state level and different socio-economical classes. Incorporating network structure, our detailed analysis highlights that high-income level residents changed their recreational behavior by visiting their local parks more and a broader recreational options outside of their local census area; whereas the low-income residents changed their visitation behavior by reducing their recreational choices. 

Continual Federated Learning (CFL) is a distributed machine learning technique that enables multiple clients to collaboratively train a shared model without sharing their data, while also adapting to new classes without forgetting previously learned ones. This dynamic, adaptive learning process parallels the concept of founda- tion models in FL, where large, pre-trained models are fine-tuned in a decentralized, federated setting. While foundation models in FL leverage pre-trained knowledge as a starting point, CFL continu- ously updates the shared model as new tasks and data distributions emerge, requiring ongoing adaptation. Currently, there are limited evaluation models and metrics in measuring fairness in CFL, and ensuring fairness over time can be challenging as the system evolves. To address this challenge, this article explores temporal fairness in CFL, examining how the fairness of the model can be influenced by the selection and participation of clients over time. Based on individual fairness, we introduce a novel fairness metric that captures temporal aspects of client behavior and evaluates different client selection strategies for their impact on promoting fairness. 

Urban population growth has significantly complicated the management of mobility systems, demanding innovative tools for planning. Generative Crowd-Flow  (GCF) models, which leverage machine learning to simulate urban movement patterns, offer a promising solution but lack sufficient evaluation of their fairness–a critical factor for equitable urban planning. We present an approach to measure and benchmark the fairness of GCF  models by developing a first-of-its-kind set of fairness metrics specifically tailored for this purpose. Using observed flow data, we employ a stochastic biased sampling approach to generate multiple permutations of Origin-Destination  datasets, each demonstrating intentional bias. Our proposed framework allows for the comparison of multiple GCF  models to evaluate how models introduce bias in outputs. Preliminary results indicate a tradeoff between model accuracy and fairness, underscoring the need for careful consideration in the deployment of these technologies. To this end, this study bridges the gap between human mobility literature and fairness in machine learning, with potential to help urban planners and policymakers leverage GCF  models for more equitable urban infrastructure development. 

As reliance on Machine Learning (ML) systems in real-world decision-making processes grows, ensuring these systems are free of bias against sensitive demographic groups is of increasing importance. Existing techniques for automatically debiasing ML models generally require access to either the models’ internal architectures, the models’ training datasets, or both. In this paper we outline the reasons why such requirements are disadvantageous, and present an alternative novel debiasing system that is both data- and model-agnostic. We implement this system as a Reinforcement Learning Agent and through extensive experiments show that we can debias a variety of target ML model architectures over three benchmark datasets. Our results show performance comparable to data- and/or model-gnostic state-of-the-art debiasers. 

Federated learning involves training statistical models over edge devices such as mobile phones such that the training data are kept local. Federated Learning (FL) can serve as an ideal candidate for training spatial temporal models that rely on heterogeneous and potentially massive numbers of participants while preserving the privacy of highly sensitive location data. However, there are unique challenges involved with transitioning existing spatial temporal models to federated learning. In this survey article, we review the existing literature that has proposed FL-based models for predicting human mobility, traffic prediction, community detection, location-based recommendation systems, and other spatial-temporal tasks. We describe the metrics and datasets these works have been using and create a baseline of these approaches in comparison to the centralized settings. Finally, we discuss the challenges of applying spatial-temporal models in a decentralized setting and by highlighting the gaps in the literature we provide a road map and opportunities for the research community.