# Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixup

arXiv: https://arxiv.org/abs/2006.09801 · HTML: https://mlsanity.com/paper/2006.09801/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2020.

## Built on by (most cited first, 29 of 29)

- [Distributed Learning in Wireless Networks: Recent Progress and Future Challenges](https://mlsanity.com/paper/2104.02151/) (2021)
- [Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2111.14213/) (2021)
- [FedMix: Approximation of Mixup under Mean Augmented Federated Learning](https://mlsanity.com/paper/2107.00233/) (2021)
- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [Federated Learning with GAN-based Data Synthesis for Non-IID Clients](https://mlsanity.com/paper/2206.05507/) (2022)
- [Green Edge AI: A Contemporary Survey](https://mlsanity.com/paper/2312.00333/) (2023)
- [DYNAFED: Tackling Client Data Heterogeneity with Global Dynamics](https://mlsanity.com/paper/2211.10878/) (2022)
- [A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency](https://mlsanity.com/paper/2307.10655/) (2023)
- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [Decentralized and Model-Free Federated Learning: Consensus-Based Distillation in Function Space](https://mlsanity.com/paper/2104.00352/) (2021)
- [Federated Distillation: A Survey](https://mlsanity.com/paper/2404.08564/) (2024)
- [Feature Matching Data Synthesis for Non-IID Federated Learning](https://mlsanity.com/paper/2308.04761/) (2023)
- [Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestration](https://mlsanity.com/paper/2205.01423/) (2022)
- [Training Machine Learning models at the Edge: A Survey](https://mlsanity.com/paper/2403.02619/) (2024)
- [Communication-Efficient Federated Distillation with Active Data Sampling](https://mlsanity.com/paper/2203.06900/) (2022)
- [FedDKD: Federated Learning with Decentralized Knowledge Distillation](https://mlsanity.com/paper/2205.00706/) (2022)
- [Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions](https://mlsanity.com/paper/2406.10861/) (2024)
- [Federated Distillation based Indoor Localization for IoT Networks](https://mlsanity.com/paper/2205.11440/) (2022)
- [Subgraph Federated Learning for Local Generalization](https://mlsanity.com/paper/2503.03995/) (2025)
- [Knowledge Distillation in Federated Edge Learning: A Survey](https://mlsanity.com/paper/2301.05849/) (2023)
- [Unsupervised Recurrent Federated Learning for Edge Popularity Prediction in Privacy-Preserving Mobile Edge Computing Networks](https://mlsanity.com/paper/2207.00755/) (2022)
- [StatMix: Data augmentation method that relies on image statistics in federated learning](https://mlsanity.com/paper/2207.04103/) (2022)
- [Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks](https://mlsanity.com/paper/2504.17421/) (2025)
- [Robust Federated Learning against both Data Heterogeneity and Poisoning Attack via Aggregation Optimization](https://mlsanity.com/paper/2211.05554/) (2022)
- [Federated Learning-Distillation Alternation for Resource-Constrained IoT](https://mlsanity.com/paper/2505.20456/) (2025)
- [Fed-TDA: Federated Tabular Data Augmentation on Non-IID Data](https://mlsanity.com/paper/2211.13116/) (2022)
- [Heterogeneous Federated Learning Using Knowledge Codistillation](https://mlsanity.com/paper/2310.02549/) (2023)
- [Semi-Federated Learning: Convergence Analysis and Optimization of A Hybrid Learning Framework](https://mlsanity.com/paper/2310.02559/) (2023)
- [P2U: Progressive Precision Update For Efficient Model Distribution](https://mlsanity.com/paper/2506.22871/) (2025)

## Abstract (arXiv)

This letter proposes a novel communication-efficient and privacy-preserving distributed machine learning framework, coined Mix2FLD. To address uplink-downlink capacity asymmetry, local model outputs are uploaded to a server in the uplink as in federated distillation (FD), whereas global model parameters are downloaded in the downlink as in federated learning (FL). This requires a model output-to-parameter conversion at the server, after collecting additional data samples from devices. To preserve privacy while not compromising accuracy, linearly mixed-up local samples are uploaded, and inversely mixed up across different devices at the server. Numerical evaluations show that Mix2FLD achieves up to 16.7% higher test accuracy while reducing convergence time by up to 18.8% under asymmetric uplink-downlink channels compared to FL.