Dynamic Semantic Compression for CNN Inference in Multi-access Edge Computing: A Graph Reinforcement Learning-based Autoencoder
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916101921701888 |
|---|---|
| author | Li, Nan Iosifidis, Alexandros Zhang, Qi |
| author_facet | Li, Nan Iosifidis, Alexandros Zhang, Qi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_12167 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dynamic Semantic Compression for CNN Inference in Multi-access Edge Computing: A Graph Reinforcement Learning-based Autoencoder Li, Nan Iosifidis, Alexandros Zhang, Qi Image and Video Processing Artificial Intelligence Machine Learning 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. |
| title | Dynamic Semantic Compression for CNN Inference in Multi-access Edge Computing: A Graph Reinforcement Learning-based Autoencoder |
| topic | Image and Video Processing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2401.12167 |