Unified Class and Domain Incremental Learning with Mixture of Experts for Indoor Localization

TL;DR

This paper introduces MOELO, a novel continual learning framework using a mixture-of-experts architecture to improve indoor localization accuracy and robustness across diverse devices and environments, addressing domain and class shifts.

Contribution

MOELO is the first unified framework to jointly handle domain-incremental and class-incremental learning for indoor localization, enabling efficient, adaptive, and resource-friendly deployment.

Findings

Up to 25.6x improvement in mean localization error

44.5x reduction in worst-case localization error

21.5x less forgetting compared to existing methods

Abstract

Indoor localization using machine learning has gained traction due to the growing demand for location-based services. However, its long-term reliability is hindered by hardware/software variations across mobile devices, which shift the model's input distribution to create domain shifts. Further, evolving indoor environments can introduce new locations over time, expanding the output space to create class shifts, making static machine learning models ineffective over time. To address these challenges, we propose a novel unified continual learning framework for indoor localization called MOELO that, for the first time, jointly addresses domain-incremental and class-incremental learning scenarios. MOELO enables a lightweight, robust, and adaptive localization solution that can be deployed on resource-limited mobile devices and is capable of continual learning in dynamic, heterogeneous real-world settings. This is made possible by a mixture-of-experts architecture, where experts are incrementally trained per region and selected through an equiangular tight frame based gating mechanism ensuring efficient routing, and low-latency inference, all within a compact model footprint. Experimental evaluations show that MOELO achieves improvements of up to 25.6x in mean localization error, 44.5x in worst-case localization error, and 21.5x lesser forgetting compared to state-of-the-art frameworks across diverse buildings, mobile devices, and learning scenarios.