Distributed Graph Neural Network Inference With Just-In-Time Compilation For Industry-Scale Graphs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915187975520256 |
|---|---|
| author | Wu, Xiabao Liu, Yongchao Qin, Wei Hong, Chuntao |
| author_facet | Wu, Xiabao Liu, Yongchao Qin, Wei Hong, Chuntao |
| contents | Graph neural networks (GNNs) have delivered remarkable results in various fields. However, the rapid increase in the scale of graph data has introduced significant performance bottlenecks for GNN inference. Both computational complexity and memory usage have risen dramatically, with memory becoming a critical limitation. Although graph sampling-based subgraph learning methods can help mitigate computational and memory demands, they come with drawbacks such as information loss and high redundant computation among subgraphs. This paper introduces an innovative processing paradgim for distributed graph learning that abstracts GNNs with a new set of programming interfaces and leverages Just-In-Time (JIT) compilation technology to its full potential. This paradigm enables GNNs to highly exploit the computational resources of distributed clusters by eliminating the drawbacks of subgraph learning methods, leading to a more efficient inference process. Our experimental results demonstrate that on industry-scale graphs of up to \textbf{500 million nodes and 22.4 billion edges}, our method can produce a performance boost of up to \textbf{27.4 times}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06208 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Distributed Graph Neural Network Inference With Just-In-Time Compilation For Industry-Scale Graphs Wu, Xiabao Liu, Yongchao Qin, Wei Hong, Chuntao Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing Graph neural networks (GNNs) have delivered remarkable results in various fields. However, the rapid increase in the scale of graph data has introduced significant performance bottlenecks for GNN inference. Both computational complexity and memory usage have risen dramatically, with memory becoming a critical limitation. Although graph sampling-based subgraph learning methods can help mitigate computational and memory demands, they come with drawbacks such as information loss and high redundant computation among subgraphs. This paper introduces an innovative processing paradgim for distributed graph learning that abstracts GNNs with a new set of programming interfaces and leverages Just-In-Time (JIT) compilation technology to its full potential. This paradigm enables GNNs to highly exploit the computational resources of distributed clusters by eliminating the drawbacks of subgraph learning methods, leading to a more efficient inference process. Our experimental results demonstrate that on industry-scale graphs of up to \textbf{500 million nodes and 22.4 billion edges}, our method can produce a performance boost of up to \textbf{27.4 times}. |
| title | Distributed Graph Neural Network Inference With Just-In-Time Compilation For Industry-Scale Graphs |
| topic | Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2503.06208 |