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

TL;DR

OMEGA is a system designed to enable low-latency GNN serving on large graphs by using selective recomputation and computation graph parallelism, reducing latency and communication overhead with minimal accuracy loss.

Contribution

The paper introduces OMEGA, a novel GNN serving system that combines selective recomputation and parallelism to improve efficiency on large graphs.

Findings

OMEGA achieves significantly lower latency compared to existing methods.

The system maintains high accuracy with minimal recomputation.

It effectively reduces communication overhead through parallelism.

Abstract

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.