YOSO: You-Only-Sample-Once via Compressed Sensing for Graph Neural Network Training
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_ | 1866915010053144576 |
|---|---|
| author | Li, Yi Guo, Zhichun Li, Guanpeng Li, Bingzhe |
| author_facet | Li, Yi Guo, Zhichun Li, Guanpeng Li, Bingzhe |
| contents | Graph neural networks (GNNs) have become essential tools for analyzing non-Euclidean data across various domains. During training stage, sampling plays an important role in reducing latency by limiting the number of nodes processed, particularly in large-scale applications. However, as the demand for better prediction performance grows, existing sampling algorithms become increasingly complex, leading to significant overhead. To mitigate this, we propose YOSO (You-Only-Sample-Once), an algorithm designed to achieve efficient training while preserving prediction accuracy. YOSO introduces a compressed sensing (CS)-based sampling and reconstruction framework, where nodes are sampled once at input layer, followed by a lossless reconstruction at the output layer per epoch. By integrating the reconstruction process with the loss function of specific learning tasks, YOSO not only avoids costly computations in traditional compressed sensing (CS) methods, such as orthonormal basis calculations, but also ensures high-probability accuracy retention which equivalent to full node participation. Experimental results on node classification and link prediction demonstrate the effectiveness and efficiency of YOSO, reducing GNN training by an average of 75\% compared to state-of-the-art methods, while maintaining accuracy on par with top-performing baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_05693 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | YOSO: You-Only-Sample-Once via Compressed Sensing for Graph Neural Network Training Li, Yi Guo, Zhichun Li, Guanpeng Li, Bingzhe Machine Learning Graph neural networks (GNNs) have become essential tools for analyzing non-Euclidean data across various domains. During training stage, sampling plays an important role in reducing latency by limiting the number of nodes processed, particularly in large-scale applications. However, as the demand for better prediction performance grows, existing sampling algorithms become increasingly complex, leading to significant overhead. To mitigate this, we propose YOSO (You-Only-Sample-Once), an algorithm designed to achieve efficient training while preserving prediction accuracy. YOSO introduces a compressed sensing (CS)-based sampling and reconstruction framework, where nodes are sampled once at input layer, followed by a lossless reconstruction at the output layer per epoch. By integrating the reconstruction process with the loss function of specific learning tasks, YOSO not only avoids costly computations in traditional compressed sensing (CS) methods, such as orthonormal basis calculations, but also ensures high-probability accuracy retention which equivalent to full node participation. Experimental results on node classification and link prediction demonstrate the effectiveness and efficiency of YOSO, reducing GNN training by an average of 75\% compared to state-of-the-art methods, while maintaining accuracy on par with top-performing baselines. |
| title | YOSO: You-Only-Sample-Once via Compressed Sensing for Graph Neural Network Training |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2411.05693 |