# Energy-Efficient Model Compression and Splitting for Collaborative Inference Over Time-Varying Channels

arXiv: https://arxiv.org/abs/2106.00995 · HTML: https://mlsanity.com/paper/2106.00995/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 18 references that are in the map.
- First posted on arXiv 2 Jun 2021.

## Builds on (most cited first, 5 of 5)

- [Improving Device-Edge Cooperative Inference of Deep Learning via 2-Step Pruning](https://mlsanity.com/paper/1903.03472/) (2019)
- [Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning](https://mlsanity.com/paper/2007.01790/) (2020)
- [A Speculative Study on 6G](https://mlsanity.com/paper/1902.06700/) (2019)
- [Vehicular Cooperative Perception Through Action Branching and Federated Reinforcement Learning](https://mlsanity.com/paper/2012.03414/) (2020)
- [Autodidactic Neurosurgeon: Collaborative Deep Inference for Mobile Edge Intelligence via Online Learning](https://mlsanity.com/paper/2102.02638/) (2021)

## Built on by (most cited first, 4 of 4)

- [Green Edge AI: A Contemporary Survey](https://mlsanity.com/paper/2312.00333/) (2023)
- [Training Latency Minimization for Model-Splitting Allowed Federated Edge Learning](https://mlsanity.com/paper/2307.11532/) (2023)
- [Socialized Learning: A Survey of the Paradigm Shift for Edge Intelligence in Networked Systems](https://mlsanity.com/paper/2404.13348/) (2024)
- [Reducing Storage of Pretrained Neural Networks by Rate-Constrained Quantization and Entropy Coding](https://mlsanity.com/paper/2505.18758/) (2025)

## Abstract (arXiv)

Today's intelligent applications can achieve high performance accuracy using machine learning (ML) techniques, such as deep neural networks (DNNs). Traditionally, in a remote DNN inference problem, an edge device transmits raw data to a remote node that performs the inference task. However, this may incur high transmission energy costs and puts data privacy at risk. In this paper, we propose a technique to reduce the total energy bill at the edge device by utilizing model compression and time-varying model split between the edge and remote nodes. The time-varying representation accounts for time-varying channels and can significantly reduce the total energy at the edge device while maintaining high accuracy (low loss). We implement our approach in an image classification task using the MNIST dataset, and the system environment is simulated as a trajectory navigation scenario to emulate different channel conditions. Numerical simulations show that our proposed solution results in minimal energy consumption and CO2 emission compared to the considered baselines while exhibiting robust performance across different channel conditions and bandwidth regime choices.