# Communication and Energy Efficient Slimmable Federated Learning via Superposition Coding and Successive Decoding

arXiv: https://arxiv.org/abs/2112.03267 · HTML: https://mlsanity.com/paper/2112.03267/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 5 Dec 2021.

## Builds on (most cited first, 14 of 14)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [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)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [Slimmable Neural Networks](https://mlsanity.com/paper/1812.08928/) (2018)
- [Universally Slimmable Networks and Improved Training Techniques](https://mlsanity.com/paper/1903.05134/) (2019)
- [Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications](https://mlsanity.com/paper/2008.02608/) (2020)
- [Federated Knowledge Distillation](https://mlsanity.com/paper/2011.02367/) (2020)
- [Federated Learning for Ultra-Reliable Low-Latency V2V Communications](https://mlsanity.com/paper/1805.09253/) (2018)
- [Communication-Efficient Massive UAV Online Path Control: Federated Learning Meets Mean-Field Game Theory](https://mlsanity.com/paper/2003.04451/) (2020)
- [Communication-Efficient and Personalized Federated Lottery Ticket Learning](https://mlsanity.com/paper/2104.12501/) (2021)
- [URLLC-eMBB Slicing to Support VR Multimodal Perceptions over Wireless Cellular Systems](https://mlsanity.com/paper/1805.00142/) (2018)

## Abstract (arXiv)

Mobile devices are indispensable sources of big data. Federated learning (FL) has a great potential in exploiting these private data by exchanging locally trained models instead of their raw data. However, mobile devices are often energy limited and wirelessly connected, and FL cannot cope flexibly with their heterogeneous and time-varying energy capacity and communication throughput, limiting the adoption. Motivated by these issues, we propose a novel energy and communication efficient FL framework, coined SlimFL. To resolve the heterogeneous energy capacity problem, each device in SlimFL runs a width-adjustable slimmable neural network (SNN). To address the heterogeneous communication throughput problem, each full-width (1.0x) SNN model and its half-width (0.5x) model are superposition-coded before transmission, and successively decoded after reception as the 0.5x or 1.0x model depending on the channel quality. Simulation results show that SlimFL can simultaneously train both 0.5x and 1.0x models with reasonable accuracy and convergence speed, compared to its vanilla FL counterpart separately training the two models using 2x more communication resources. Surprisingly, SlimFL achieves even higher accuracy with lower energy footprints than vanilla FL for poor channels and non-IID data distributions, under which vanilla FL converges slowly.