DAILOC: Domain-Incremental Learning for Indoor Localization using Smartphones

2025-06-18

AI Summary

To address the spatiotemporal domain shift in smartphone Wi-Fi fingerprint-based indoor localization—arising from device heterogeneity and environmental temporal evolution—this paper proposes the first incremental learning framework jointly modeling spatial and temporal domain adaptation. Methodologically, it integrates domain-agnostic representation learning, memory replay, and latent-space alignment. Specifically: (1) a multi-level variational autoencoder disentangles invariant features across devices and environments; (2) a memory-guided class-wise latent-space alignment mechanism mitigates catastrophic forgetting. Extensive experiments across multiple smartphones, buildings, and time periods demonstrate that the method reduces mean localization error by 2.74× and worst-case error by 4.6× compared to state-of-the-art approaches, establishing new performance benchmarks for robust, adaptive Wi-Fi fingerprinting.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Wi-Fi fingerprinting-based indoor localization faces significant challenges in real-world deployments due to domain shifts arising from device heterogeneity and temporal variations within indoor environments. Existing approaches often address these issues independently, resulting in poor generalization and susceptibility to catastrophic forgetting over time. In this work, we propose DAILOC, a novel domain-incremental learning framework that jointly addresses both temporal and device-induced domain shifts. DAILOC introduces a novel disentanglement strategy that separates domain shifts from location-relevant features using a multi-level variational autoencoder. Additionally, we introduce a novel memory-guided class latent alignment mechanism to address the effects of catastrophic forgetting over time. Experiments across multiple smartphones, buildings, and time instances demonstrate that DAILOC significantly outperforms state-of-the-art methods, achieving up to 2.74x lower average error and 4.6x lower worst-case error.

Problem

• Addresses domain shifts in Wi-Fi fingerprinting for indoor localization
• Mitigates catastrophic forgetting in incremental learning scenarios
• Improves accuracy across diverse devices and temporal variations

Innovation

• Domain-incremental learning for Wi-Fi fingerprinting
• Multi-level variational autoencoder for feature disentanglement
• Memory-guided latent alignment against catastrophic forgetting