OMEGA: A Low-Latency GNN Serving System for Large Graphs
This addresses the problem of efficient GNN serving for large-scale graph applications, representing an incremental advance in system optimization.
The paper tackles the challenge of high latency in serving Graph Neural Networks (GNNs) on large graphs by proposing OMEGA, a system that reduces latency with minimal accuracy loss, achieving significant performance improvements over state-of-the-art techniques.
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.