# FedFusion: Federated Learning with Diversity- and Cluster-Aware Encoders for Robust Adaptation under Label Scarcity

arXiv: https://arxiv.org/abs/2509.19220 · HTML: https://mlsanity.com/paper/2509.19220/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## Builds on (most cited first, 19 of 19)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [Flower: A Friendly Federated Learning Research Framework](https://mlsanity.com/paper/2007.14390/) (2020)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [Federated Adversarial Domain Adaptation](https://mlsanity.com/paper/1911.02054/) (2019)
- [Personalized Federated Learning with Feature Alignment and Classifier Collaboration](https://mlsanity.com/paper/2306.11867/) (2023)
- [Self-supervised Domain Adaptation for Computer Vision Tasks](https://mlsanity.com/paper/1907.10915/) (2019)
- [Feature Distribution Matching for Federated Domain Generalization](https://mlsanity.com/paper/2203.11635/) (2022)
- [Randomized Quantization is All You Need for Differential Privacy in Federated Learning](https://mlsanity.com/paper/2306.11913/) (2023)
- [Federated Learning in Practice: Reflections and Projections](https://mlsanity.com/paper/2410.08892/) (2024)
- [A Comprehensive Survey of Federated Transfer Learning: Challenges, Methods and Applications](https://mlsanity.com/paper/2403.01387/) (2024)
- [Post Quantum Secure Blockchain-based Federated Learning for Mobile Edge Computing](https://mlsanity.com/paper/2302.13258/) (2023)
- [Multi-task Federated Learning with Encoder-Decoder Structure: Enabling Collaborative Learning Across Different Tasks](https://mlsanity.com/paper/2504.09800/) (2025)
- [Federated Learning in Adversarial Environments: Testbed Design and Poisoning Resilience in Cybersecurity](https://mlsanity.com/paper/2409.09794/) (2024)
- [FedFeat+: A Robust Federated Learning Framework Through Federated Aggregation and Differentially Private Feature-Based Classifier Retraining](https://mlsanity.com/paper/2504.06004/) (2025)

## Abstract (arXiv)

Federated learning in practice must contend with heterogeneous feature spaces, severe non-IID data, and scarce labels across clients. We present FedFusion, a federated transfer-learning framework that unifies domain adaptation and frugal labelling with diversity-/cluster-aware encoders (DivEn, DivEn-mix, DivEn-c). Labelled teacher clients guide learner clients via confidence-filtered pseudo-labels and domain-adaptive transfer, while clients maintain personalised encoders tailored to local data. To preserve global coherence under heterogeneity, FedFusion employs similarity-weighted classifier coupling (with optional cluster-wise averaging), mitigating dominance by data-rich sites and improving minority-client performance. The frugal-labelling pipeline combines self-/semi-supervised pretext training with selective fine-tuning, reducing annotation demands without sharing raw data. Across tabular and imaging benchmarks under IID, non-IID, and label-scarce regimes, FedFusion consistently outperforms state-of-the-art baselines in accuracy, robustness, and fairness while maintaining comparable communication and computation budgets. These results show that harmonising personalisation, domain adaptation, and label efficiency is an effective recipe for robust federated learning under real-world constraints.