# 5G-DIL: Domain Incremental Learning with Similarity-Aware Sampling for Dynamic 5G Indoor Localization

arXiv: https://arxiv.org/abs/2505.17684 · HTML: https://mlsanity.com/paper/2505.17684/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 23 of 23)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions](https://mlsanity.com/paper/2204.08817/) (2022)
- [A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm](https://mlsanity.com/paper/2310.12244/) (2023)
- [Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift](https://mlsanity.com/paper/2204.03342/) (2022)
- [Prediction Error-based Classification for Class-Incremental Learning](https://mlsanity.com/paper/2305.18806/) (2023)
- [Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learning](https://mlsanity.com/paper/2405.11067/) (2024)
- [Evaluating ML Robustness in GNSS Interference Classification, Characterization & Localization](https://mlsanity.com/paper/2409.15114/) (2024)
- [A Tutorial on Terahertz-Band Localization for 6G Communication Systems](https://mlsanity.com/paper/2110.08581/) (2021)
- [Improving Replay-Based Continual Semantic Segmentation with Smart Data Selection](https://mlsanity.com/paper/2209.09839/) (2022)
- [Improving Replay Sample Selection and Storage for Less Forgetting in Continual Learning](https://mlsanity.com/paper/2308.01895/) (2023)
- [Federated Learning with MMD-based Early Stopping for Adaptive GNSS Interference Classification](https://mlsanity.com/paper/2410.15681/) (2024)
- [Multi-Environment based Meta-Learning with CSI Fingerprints for Radio Based Positioning](https://mlsanity.com/paper/2210.14510/) (2022)
- [Deep Learning based Positioning with Multi-task Learning and Uncertainty-based Fusion](https://mlsanity.com/paper/2403.08565/) (2024)
- [Temporal Source Recovery for Time-Series Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2409.19635/) (2024)
- [Graph-Based vs. Error State Kalman Filter-Based Fusion Of 5G And Inertial Data For MAV Indoor Pose Estimation](https://mlsanity.com/paper/2404.00691/) (2024)
- [FeMLoc: Federated Meta-learning for Adaptive Wireless Indoor Localization Tasks in IoT Networks](https://mlsanity.com/paper/2405.11079/) (2024)
- [Wiometrics: Comparative Performance of Artificial Neural Networks for Wireless Navigation](https://mlsanity.com/paper/2309.02121/) (2023)
- [5G Positioning Advancements with AI/ML](https://mlsanity.com/paper/2401.02427/) (2023)
- [Neural 5G Indoor Localization with IMU Supervision](https://mlsanity.com/paper/2402.09948/) (2024)
- [One-Shot Domain Incremental Learning](https://mlsanity.com/paper/2403.16707/) (2024)

## Built on by (most cited first, 1 of 1)

- [Physics-Informed Domain-Invariant Feature Learning with Autoencoder-Driven Gaussian Clustering for Robust Non-line-of-Sight Scenarios](https://mlsanity.com/paper/2607.02537/) (2026)

## Abstract (arXiv)

Indoor positioning based on 5G data has achieved high accuracy through the adoption of recent machine learning (ML) techniques. However, the performance of learning-based methods degrades significantly when environmental conditions change, thereby hindering their applicability to new scenarios. Acquiring new training data for each environmental change and fine-tuning ML models is both time-consuming and resource-intensive. This paper introduces a domain incremental learning (DIL) approach for dynamic 5G indoor localization, called 5G-DIL, enabling rapid adaptation to environmental changes. We present a novel similarity-aware sampling technique based on the Chebyshev distance, designed to efficiently select specific exemplars from the previous environment while training only on the modified regions of the new environment. This avoids the need to train on the entire region, significantly reducing the time and resources required for adaptation without compromising localization accuracy. This approach requires as few as 50 exemplars from adaptation domains, significantly reducing training time while maintaining high positioning accuracy in previous environments. Comparative evaluations against state-of-the-art DIL techniques on a challenging real-world indoor dataset demonstrate the effectiveness of the proposed sample selection method. Our approach is adaptable to real-world non-line-of-sight propagation scenarios and achieves an MAE positioning error of 0.261 meters, even under dynamic environmental conditions. Code: https://gitlab.cc-asp.fraunhofer.de/5g-pos/5g-dil