OMEGA: A Low-Latency GNN Serving System for Large 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_ | 1866912189588176896 |
|---|---|
| author | Kim, Geon-Woo Kim, Donghyun Moon, Jeongyoon Liu, Henry Khan, Tarannum Iyer, Anand Kim, Daehyeok Akella, Aditya |
| author_facet | Kim, Geon-Woo Kim, Donghyun Moon, Jeongyoon Liu, Henry Khan, Tarannum Iyer, Anand Kim, Daehyeok Akella, Aditya |
| contents | Graph Neural Networks (GNNs) have been widely adopted for their ability to compute expressive node representations in graph datasets. However, serving GNNs on large graphs is challenging due to the high communication, computation, and memory overheads of constructing and executing computation graphs, which represent information flow across large neighborhoods. Existing approximation techniques in training can mitigate the overheads but, in serving, still lead to high latency and/or accuracy loss. To this end, we propose OMEGA, a system that enables low-latency GNN serving for large graphs with minimal accuracy loss through two key ideas. First, OMEGA employs selective recomputation of precomputed embeddings, which allows for reusing precomputed computation subgraphs while selectively recomputing a small fraction to minimize accuracy loss. Second, we develop computation graph parallelism, which reduces communication overhead by parallelizing the creation and execution of computation graphs across machines. Our evaluation with large graph datasets and GNN models shows that OMEGA significantly outperforms state-of-the-art techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_08547 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OMEGA: A Low-Latency GNN Serving System for Large Graphs Kim, Geon-Woo Kim, Donghyun Moon, Jeongyoon Liu, Henry Khan, Tarannum Iyer, Anand Kim, Daehyeok Akella, Aditya Distributed, Parallel, and Cluster Computing Machine Learning Graph Neural Networks (GNNs) have been widely adopted for their ability to compute expressive node representations in graph datasets. However, serving GNNs on large graphs is challenging due to the high communication, computation, and memory overheads of constructing and executing computation graphs, which represent information flow across large neighborhoods. Existing approximation techniques in training can mitigate the overheads but, in serving, still lead to high latency and/or accuracy loss. To this end, we propose OMEGA, a system that enables low-latency GNN serving for large graphs with minimal accuracy loss through two key ideas. First, OMEGA employs selective recomputation of precomputed embeddings, which allows for reusing precomputed computation subgraphs while selectively recomputing a small fraction to minimize accuracy loss. Second, we develop computation graph parallelism, which reduces communication overhead by parallelizing the creation and execution of computation graphs across machines. Our evaluation with large graph datasets and GNN models shows that OMEGA significantly outperforms state-of-the-art techniques. |
| title | OMEGA: A Low-Latency GNN Serving System for Large Graphs |
| topic | Distributed, Parallel, and Cluster Computing Machine Learning |
| url | https://arxiv.org/abs/2501.08547 |