paper-with-me

홈 › Papers

OMEGA: A Low-Latency GNN Serving System for Large Graphs

2025-01-15 · Geon-Woo Kim, Donghyun Kim, Jeongyoon Moon, Henry Liu, Tarannum Khan, Anand Iyer, Daehyeok Kim, Aditya Akella

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.

📄 PDF Abstract BibTeX arXiv:2501.08547

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Efficient Vector Search in the Wild: One Model for Multi-K Queries

2026-03-06 · Yifan Peng, Jiafei Fan, Xingda Wei, Sijie Shen 외 arxiv

Learned top-K search is a promising approach for serving vector queries with both high accuracy and performance. However, current models trained for a specific K value fail to generalize to real-world multi-K queries: th…

Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow

2024-06-03 · Yixuan Mei, Yonghao Zhuang, Xupeng Miao, Juncheng Yang 외

This paper introduces Helix, a distributed system for high-throughput, low-latency large language model (LLM) serving in heterogeneous GPU clusters. The key idea behind Helix is to formulate inference computation of LLMs…

GPULanguage ModelingLanguage ModellingLarge Language Model+1

Foundry: Template-Based CUDA Graph Context Materialization for Fast LLM Serving Cold Start

2026-04-08 · Xueshen Liu, Yongji Wu, Yuncheng Yao, Danyang Zhuo 외 arxiv

Modern LLM service providers increasingly rely on autoscaling and parallelism reconfiguration to respond to rapidly changing workloads, but cold-start latency remains a major bottleneck. While recent systems have reduced…

STAG: Enabling Low Latency and Low Staleness of GNN-based Services with Dynamic Graphs

2023-09-27 · Jiawen Wang, Quan Chen, Deze Zeng, Zhuo Song 외

Many emerging user-facing services adopt Graph Neural Networks (GNNs) to improve serving accuracy. When the graph used by a GNN model changes, representations (embedding) of nodes in the graph should be updated according…

Graph Neural Network Acceleration via Matrix Dimension Reduction

2021-01-01 · Shunhua Jiang, Yunze Man, Zhao Song, Danyang Zhuo

Graph Neural Networks (GNNs) have become the de facto method for machine learning on graph data (e.g., social networks, protein structures, code ASTs), but they require significant time and resource to train. One alterna…

Dimensionality ReductionGraph Neural Network