# Interpretable Physics Informed WiFi Indoor Localization: Learning an Effective Access Point Geometry and Using It to Prune

arXiv: https://arxiv.org/abs/2609.32539 · HTML: https://mlsanity.com/paper/2609.32539/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 40 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Understanding over-squashing and bottlenecks on graphs via curvature](https://mlsanity.com/paper/2111.14522/) (2021)
- [Low-effort place recognition with WiFi fingerprints using deep learning](https://mlsanity.com/paper/1611.02049/) (2016)
- [Federated Learning based Hierarchical 3D Indoor Localization](https://mlsanity.com/paper/2303.00450/) (2023)
- [MG-HGNN: A Heterogeneous GNN Framework for Indoor Wi-Fi Fingerprint-Based Localization](https://mlsanity.com/paper/2511.07282/) (2025)

## Abstract (arXiv)

Deep learning models can achieve high accuracy for indoor localization, but their black-box nature limits interpretability and the reuse of learned information. We propose a hierarchical deep learning framework for WiFi fingerprint-based indoor localization that jointly predicts user location and learns an effective geometry of the surrounding access points (APs). Physics-informed decoders infer this geometry directly from RSSI measurements and labelled user positions, without requiring the true AP coordinates during training. The learned geometry is then used to rank and prune APs. On the UJIIndoorLoc dataset, the proposed chained model achieves a mean 3D localization error of 7.07 m, reducing error by 26% to 36% compared with baseline models. Previously published methods evaluated on the same official split report errors 10.6% to 31.0% higher. Pruning 35% or 50% of the APs causes only a small loss in localization accuracy. The inferred geometry also enables Fisher-information-based AP ranking even when fingerprint databases do not contain surveyed AP coordinates. Experiments on the Tampere/TUT and UTSIndoorLoc datasets show that geometry-guided AP selection performs comparably to selectors built directly from labelled data. These results show that physics-informed interpretability can improve indoor localization while also supporting effective feature selection.