FairDRL-ST: Disentangled Representation Learning for Fair Spatio-Temporal Mobility Prediction

2025-08-10

AI Summary

This work addresses group unfairness in spatiotemporal forecasting—particularly urban mobility demand prediction—by proposing an unsupervised fairness learning framework. The method leverages disentangled representation learning and adversarial training to explicitly decouple sensitive attributes (e.g., demographic or geographic features) from the latent representations of deep spatiotemporal neural networks, thereby circumventing the risk of overcorrection inherent in supervised debiasing approaches. Experiments on real-world urban mobility datasets demonstrate that the proposed approach maintains predictive accuracy comparable to state-of-the-art models while substantially reducing inter-group prediction error disparities; fairness metrics improve by up to 23.6%. Its core contribution is the first formulation of fairness-aware spatiotemporal forecasting without requiring labeled sensitive attributes—yielding a deployable, interpretable, and ethically compliant technical pathway for AI-driven public services.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Ethics, Bias, and Fairness

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

As deep spatio-temporal neural networks are increasingly utilised in urban computing contexts, the deployment of such methods can have a direct impact on users of critical urban infrastructure, such as public transport, emergency services, and traffic management systems. While many spatio-temporal methods focus on improving accuracy, fairness has recently gained attention due to growing evidence that biased predictions in spatio-temporal applications can disproportionately disadvantage certain demographic or geographic groups, thereby reinforcing existing socioeconomic inequalities and undermining the ethical deployment of AI in public services. In this paper, we propose a novel framework, FairDRL-ST, based on disentangled representation learning, to address fairness concerns in spatio-temporal prediction, with a particular focus on mobility demand forecasting. By leveraging adversarial learning and disentangled representation learning, our framework learns to separate attributes that contain sensitive information. Unlike existing methods that enforce fairness through supervised learning, which may lead to overcompensation and degraded performance, our framework achieves fairness in an unsupervised manner with minimal performance loss. We apply our framework to real-world urban mobility datasets and demonstrate its ability to close fairness gaps while delivering competitive predictive performance compared to state-of-the-art fairness-aware methods.

Problem

• Address fairness in spatio-temporal mobility prediction
• Separate sensitive attributes using disentangled representation learning
• Reduce fairness gaps without significant performance loss

Innovation

• Disentangled representation learning for fairness
• Adversarial learning separates sensitive attributes
• Unsupervised fairness with minimal performance loss