Device-Induced Mobility Heterogeneity and Its Impact on Federated Next-Location Prediction
This paper investigates the impact of device-level mobility heterogeneity on federated learning and proposes a tier-aware client selection approach to improve fairness in next-location prediction.
This paper is novel in its large-scale measurement study of device-level mobility heterogeneity and its proposal of a tier-aware client selection approach to improve fairness in federated learning.
Before reading this…
Applications
- →Network management
- →Urban planning
- →Location-based services
To understand this paper, make sure you know these concepts first:
- Federated learningfind papers →
- Mobility data analysisfind papers →
Abstract
More Like ThisPredicting human mobility is central to network management, urban planning, and location-based services, yet privacy concerns are increasingly pushing such tasks toward federated learning. A key challenge in this setting is the strong heterogeneity of mobility data across users, which leads to non-IID data distributions and can significantly impact model performance and fairness. In this paper, we present a large-scale measurement study of device-level mobility heterogeneity using data from a major MNO in a dense European capital. Our dataset comprises mobility traces derived from network events, covering over 50,000 UEs across 178 smartphone models. We group devices into tiers based on their market segment and show that mobility characteristics, such as spatial range and regularity, vary systematically across these tiers, revealing a previously underexplored source of bias in mobility data. We investigate the implications of this heterogeneity on the use case of federated next-location prediction. In particular, we find that balancing device tiers across silos through tier-aware client selection yields the best results, improving fairness by up to 34.49% without degrading accuracy. In contrast, a FedProx-only approach achieves a 21.46% fairness improvement, offering a reasonable alternative when device information is unavailable, though with lower overall gains.