# Dynamic Semantic Compression for CNN Inference in Multi-access Edge Computing: A Graph Reinforcement Learning-based Autoencoder

arXiv: https://arxiv.org/abs/2401.12167 · HTML: https://mlsanity.com/paper/2401.12167/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 19 Jan 2024.

## Placed in

- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [CVXPY: A Python-Embedded Modeling Language for Convex Optimization](https://mlsanity.com/paper/1603.00943/) (2016)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [Learning Convolutional Neural Networks for Graphs](https://mlsanity.com/paper/1605.05273/) (2016)
- [Convolutional Networks with Adaptive Inference Graphs](https://mlsanity.com/paper/1711.11503/) (2017)
- [Dynamic Channel Pruning: Feature Boosting and Suppression](https://mlsanity.com/paper/1810.05331/) (2018)
- [Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges](https://mlsanity.com/paper/2103.04505/) (2021)
- [BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems](https://mlsanity.com/paper/1910.14315/) (2019)
- [Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks](https://mlsanity.com/paper/2303.15991/) (2023)
- [Compute and Energy Consumption Trends in Deep Learning Inference](https://mlsanity.com/paper/2109.05472/) (2021)
- [Wireless Image Retrieval at the Edge](https://mlsanity.com/paper/2007.10915/) (2020)
- [You Look Twice: GaterNet for Dynamic Filter Selection in CNNs](https://mlsanity.com/paper/1811.11205/) (2018)
- [Gated Channel Transformation for Visual Recognition](https://mlsanity.com/paper/1909.11519/) (2019)
- [Dynamic Split Computing for Efficient Deep Edge Intelligence](https://mlsanity.com/paper/2205.11269/) (2022)
- [Joint Task Offloading and Resource Allocation for Multi-Server Mobile-Edge Computing Networks](https://mlsanity.com/paper/1705.00704/) (2017)
- [Improving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum Learning](https://mlsanity.com/paper/2104.10461/) (2021)
- [Empirical analysis of non-linear activation functions for Deep Neural Networks in classification tasks](https://mlsanity.com/paper/1710.11272/) (2017)
- [Attention-based Feature Compression for CNN Inference Offloading in Edge Computing](https://mlsanity.com/paper/2211.13745/) (2022)

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

- [Semantic Edge Computing and Semantic Communications in 6G Networks: A Unifying Survey and Research Challenges](https://mlsanity.com/paper/2411.18199/) (2024)
- [Goal-Oriented Semantic Communication for Wireless Image Transmission via Stable Diffusion](https://mlsanity.com/paper/2408.00428/) (2024)
- [GraphEdge: Dynamic Graph Partition and Task Scheduling for GNNs Computing in Edge Network](https://mlsanity.com/paper/2504.15905/) (2025)
- [PRISM: Distributed Inference for Foundation Models at Edge](https://mlsanity.com/paper/2507.12145/) (2025)

## Abstract (arXiv)

This paper studies the computational offloading of CNN inference in dynamic multi-access edge computing (MEC) networks. To address the uncertainties in communication time and computation resource availability, we propose a novel semantic compression method, autoencoder-based CNN architecture (AECNN), for effective semantic extraction and compression in partial offloading. In the semantic encoder, we introduce a feature compression module based on the channel attention mechanism in CNNs, to compress intermediate data by selecting the most informative features. In the semantic decoder, we design a lightweight decoder to reconstruct the intermediate data through learning from the received compressed data to improve accuracy. To effectively trade-off communication, computation, and inference accuracy, we design a reward function and formulate the offloading problem of CNN inference as a maximization problem with the goal of maximizing the average inference accuracy and throughput over the long term. To address this maximization problem, we propose a graph reinforcement learning-based AECNN (GRL-AECNN) method, which outperforms existing works DROO-AECNN, GRL-BottleNet++ and GRL-DeepJSCC under different dynamic scenarios. This highlights the advantages of GRL-AECNN in offloading decision-making in dynamic MEC.