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

arXiv: https://arxiv.org/abs/2511.17829 · HTML: https://mlsanity.com/paper/2511.17829/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 21 Nov 2025.

## Builds on (most cited first, 18 of 18)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Uncertainty-based Continual Learning with Adaptive Regularization](https://mlsanity.com/paper/1905.11614/) (2019)
- [Fixed Design Analysis of Regularization-Based Continual Learning](https://mlsanity.com/paper/2303.10263/) (2023)
- [Multi-Head Attention Neural Network for Smartphone Invariant Indoor Localization](https://mlsanity.com/paper/2205.08069/) (2022)
- [CHISEL: Compression-Aware High-Accuracy Embedded Indoor Localization with Deep Learning](https://mlsanity.com/paper/2107.01192/) (2021)
- [FedHIL: Heterogeneity Resilient Federated Learning for Robust Indoor Localization with Mobile Devices](https://mlsanity.com/paper/2307.01780/) (2023)
- [Siamese Neural Encoders for Long-Term Indoor Localization with Mobile Devices](https://mlsanity.com/paper/2112.00654/) (2021)
- [STELLAR: Siamese Multi-Headed Attention Neural Networks for Overcoming Temporal Variations and Device Heterogeneity with Indoor Localization](https://mlsanity.com/paper/2312.10312/) (2023)
- [SANGRIA: Stacked Autoencoder Neural Networks with Gradient Boosting for Indoor Localization](https://mlsanity.com/paper/2403.01348/) (2024)
- [CALLOC: Curriculum Adversarial Learning for Secure and Robust Indoor Localization](https://mlsanity.com/paper/2311.06361/) (2023)
- [12 mJ per Class On-Device Online Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2403.07851/) (2024)
- [SENTINEL: Securing Indoor Localization against Adversarial Attacks with Capsule Neural Networks](https://mlsanity.com/paper/2407.11091/) (2024)
- [AI and Machine Learning Driven Indoor Localization and Navigation with Mobile Embedded Systems](https://mlsanity.com/paper/2408.04797/) (2024)
- [DAILOC: Domain-Incremental Learning for Indoor Localization using Smartphones](https://mlsanity.com/paper/2506.15554/) (2025)
- [GATE: Graph Attention Neural Networks with Real-Time Edge Construction for Robust Indoor Localization using Mobile Embedded Devices](https://mlsanity.com/paper/2507.11053/) (2025)

## Abstract (arXiv)

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.