ECC-SNN: Cost-Effective Edge-Cloud Collaboration for Spiking Neural Networks

Authors: Di Yu, Changze Lv, Xin Du, Linshan Jiang, Wentao Tong, Zhenyu Liao, Xiaoqing Zheng, Shuiguang Deng

IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experimental results on four datasets demonstrate that ECC-SNN improves accuracy by 4.15%, reduces average energy consumption by 79.4%, and lowers average processing latency by 39.1%.
Researcher Affiliation Academia 1Zhejiang University 2Fudan University 3National University of Singapore EMAIL, EMAIL, EMAIL, EMAIL EMAIL, EMAIL, EMAIL
Pseudocode Yes Algorithm 1 Collaborative Inference in ECC-SNN
Open Source Code Yes 1https://github.com/AmazingDD/ECC-SNN
Open Datasets Yes Extensive experiments on four diverse datasets demonstrate that ECC-SNN significantly outperforms standalone edge-based SNNs and cloud-based ANNs, achieving an average accuracy improvement of 4.15%, a 79.4% reduction in energy consumption, and a 39.1% decrease in processing latency. (The datasets are identified as CIFAR-10, CIFAR-100, Caltech, Tiny-Image Net in Table 1).
Dataset Splits Yes Following [Zhou et al., 2024a], we evaluate the effectiveness of our proposed ECC-SNN using the standard classincremental learning setting... We denote the data split setting as w/ B-u, Inc-v, i.e., the first dataset contains u classes, and each following dataset contains v classes. u = 0 means the total classes are equally divided into each task.
Hardware Specification No By default, we adopt the spiking VGG-9 model as the SNN deployed on the edge device featuring a neuromorphic chip [Ma et al., 2024] while utilizing a widely recognized pretrained Vi T model vit-base-patch16 as the cloud-based ANN. The paper mentions a 'neuromorphic chip' and 'server GPU' but does not specify their exact models or other detailed specifications.
Software Dependencies No The paper does not explicitly mention specific software dependencies with version numbers.
Experiment Setup Yes By default, we adopt the spiking VGG-9 model as the SNN deployed on the edge device... while utilizing a widely recognized pretrained Vi T model vit-base-patch16 as the cloud-based ANN. Also, the filtering criterion uses a 'fixed filtering threshold δ=0.3' as indicated in Figures 4, 6, and 7.