SL-ACC: A Communication-Efficient Split Learning Framework with Adaptive Channel-wise Compression
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909740849692672 |
|---|---|
| author | Lin, Zehang Lin, Zheng Yang, Miao Huang, Jianhao Zhang, Yuxin Fang, Zihan Du, Xia Chen, Zhe Zhu, Shunzhi Ni, Wei |
| author_facet | Lin, Zehang Lin, Zheng Yang, Miao Huang, Jianhao Zhang, Yuxin Fang, Zihan Du, Xia Chen, Zhe Zhu, Shunzhi Ni, Wei |
| contents | The increasing complexity of neural networks poses a significant barrier to the deployment of distributed machine learning (ML) on resource-constrained devices, such as federated learning (FL). Split learning (SL) offers a promising solution by offloading the primary computing load from edge devices to a server via model partitioning. However, as the number of participating devices increases, the transmission of excessive smashed data (i.e., activations and gradients) becomes a major bottleneck for SL, slowing down the model training. To tackle this challenge, we propose a communication-efficient SL framework, named SL-ACC, which comprises two key components: adaptive channel importance identification (ACII) and channel grouping compression (CGC). ACII first identifies the contribution of each channel in the smashed data to model training using Shannon entropy. Following this, CGC groups the channels based on their entropy and performs group-wise adaptive compression to shrink the transmission volume without compromising training accuracy. Extensive experiments across various datasets validate that our proposed SL-ACC framework takes considerably less time to achieve a target accuracy than state-of-the-art benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_12984 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SL-ACC: A Communication-Efficient Split Learning Framework with Adaptive Channel-wise Compression Lin, Zehang Lin, Zheng Yang, Miao Huang, Jianhao Zhang, Yuxin Fang, Zihan Du, Xia Chen, Zhe Zhu, Shunzhi Ni, Wei Machine Learning Artificial Intelligence Networking and Internet Architecture The increasing complexity of neural networks poses a significant barrier to the deployment of distributed machine learning (ML) on resource-constrained devices, such as federated learning (FL). Split learning (SL) offers a promising solution by offloading the primary computing load from edge devices to a server via model partitioning. However, as the number of participating devices increases, the transmission of excessive smashed data (i.e., activations and gradients) becomes a major bottleneck for SL, slowing down the model training. To tackle this challenge, we propose a communication-efficient SL framework, named SL-ACC, which comprises two key components: adaptive channel importance identification (ACII) and channel grouping compression (CGC). ACII first identifies the contribution of each channel in the smashed data to model training using Shannon entropy. Following this, CGC groups the channels based on their entropy and performs group-wise adaptive compression to shrink the transmission volume without compromising training accuracy. Extensive experiments across various datasets validate that our proposed SL-ACC framework takes considerably less time to achieve a target accuracy than state-of-the-art benchmarks. |
| title | SL-ACC: A Communication-Efficient Split Learning Framework with Adaptive Channel-wise Compression |
| topic | Machine Learning Artificial Intelligence Networking and Internet Architecture |
| url | https://arxiv.org/abs/2508.12984 |