# Improving Federated Aggregation with Deep Unfolding Networks

arXiv: https://arxiv.org/abs/2306.17362 · HTML: https://mlsanity.com/paper/2306.17362/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 30 Jun 2023.

## Builds on (most cited first, 12 of 12)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints](https://mlsanity.com/paper/1910.01991/) (2019)
- [Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing](https://mlsanity.com/paper/1912.10557/) (2019)
- [FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping](https://mlsanity.com/paper/2012.13995/) (2020)
- [A Field Guide to Federated Optimization](https://mlsanity.com/paper/2107.06917/) (2021)
- [GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learning](https://mlsanity.com/paper/2109.02053/) (2021)
- [FedExP: Speeding Up Federated Averaging via Extrapolation](https://mlsanity.com/paper/2301.09604/) (2023)
- [Deep Unfolding for Communications Systems: A Survey and Some New Directions](https://mlsanity.com/paper/1906.05774/) (2019)
- [Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization](https://mlsanity.com/paper/2201.11066/) (2022)
- [A Contribution-based Device Selection Scheme in Federated Learning](https://mlsanity.com/paper/2203.05369/) (2022)
- [Stochastic Unrolled Federated Learning](https://mlsanity.com/paper/2305.15371/) (2023)
- [Federated Deep Unfolding for Sparse Recovery](https://mlsanity.com/paper/2010.12616/) (2020)

## Abstract (arXiv)

The performance of Federated learning (FL) is negatively affected by device differences and statistical characteristics between participating clients. To address this issue, we introduce a deep unfolding network (DUN)-based technique that learns adaptive weights that unbiasedly ameliorate the adverse impacts of heterogeneity. The proposed method demonstrates impressive accuracy and quality-aware aggregation. Furthermore, it evaluated the best-weighted normalization approach to define less computational power on the aggregation method. The numerical experiments in this study demonstrate the effectiveness of this approach and provide insights into the interpretability of the unbiased weights learned. By incorporating unbiased weights into the model, the proposed approach effectively addresses quality-aware aggregation under the heterogeneity of the participating clients and the FL environment. Codes and details are hrefhttps://github.com/shanikairoshi/ImprovedDUNbasedFLAggregationhere.