# Federated Learning for Appearance-based Gaze Estimation in the Wild

arXiv: https://arxiv.org/abs/2211.07330 · HTML: https://mlsanity.com/paper/2211.07330/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Nov 2022.

## Built on by (most cited first, 7 of 7)

- [Eye-tracked Virtual Reality: A Comprehensive Survey on Methods and Privacy Challenges](https://mlsanity.com/paper/2305.14080/) (2023)
- [Mining Gaze for Contrastive Learning toward Computer-Assisted Diagnosis](https://mlsanity.com/paper/2312.06069/) (2023)
- [PrivateGaze: Preserving User Privacy in Black-box Mobile Gaze Tracking Services](https://mlsanity.com/paper/2408.00950/) (2024)
- [PrivatEyes: Appearance-based Gaze Estimation Using Federated Secure Multi-Party Computation](https://mlsanity.com/paper/2402.18970/) (2024)
- [HaHeAE: Learning Generalisable Joint Representations of Human Hand and Head Movements in Extended Reality](https://mlsanity.com/paper/2410.16430/) (2024)
- [QualitEye: Public and Privacy-preserving Gaze Data Quality Verification](https://mlsanity.com/paper/2506.05908/) (2025)
- [PrivateXR: Defending Privacy Attacks in Extended Reality Through Explainable AI-Guided Differential Privacy](https://mlsanity.com/paper/2512.16851/) (2025)

## Abstract (arXiv)

Gaze estimation methods have significantly matured in recent years, but the large number of eye images required to train deep learning models poses significant privacy risks. In addition, the heterogeneous data distribution across different users can significantly hinder the training process. In this work, we propose the first federated learning approach for gaze estimation to preserve the privacy of gaze data. We further employ pseudo-gradient optimisation to adapt our federated learning approach to the divergent model updates to address the heterogeneous nature of in-the-wild gaze data in collaborative setups. We evaluate our approach on a real-world dataset (MPIIGaze) and show that our work enhances the privacy guarantees of conventional appearance-based gaze estimation methods, handles the convergence issues of gaze estimators, and significantly outperforms vanilla federated learning by 15.8% (from a mean error of 10.63 degrees to 8.95 degrees). As such, our work paves the way to develop privacy-aware collaborative learning setups for gaze estimation while maintaining the model's performance.