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

• URL: http://arxiv.org/abs/2501.08547v1
• Date: Wed, 15 Jan 2025 03:14:18 GMT
• Title: OMEGA: A Low-Latency GNN Serving System for Large Graphs
• Authors: Geon-Woo Kim, Donghyun Kim, Jeongyoon Moon, Henry Liu, Tarannum Khan, Anand Iyer, Daehyeok Kim, Aditya Akella,
• Abstract summary: Graph Neural Networks (GNNs) have been widely adopted for their ability to compute expressive node representations in graph datasets. Existing approximation techniques in training can mitigate the overheads but, in serving, still lead to high latency and/or accuracy loss. We propose OMEGA, a system that enables low-latency GNN serving for large graphs with minimal accuracy loss.
• Score: 8.51634655687174
• License:
• 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.

Related papers

• GLISP: A Scalable GNN Learning System by Exploiting Inherent Structural Properties of Graphs [5.410321469222541]
  We propose GLISP, a sampling based GNN learning system for industrial scale graphs. GLISP consists of three core components: graph partitioner, graph sampling service and graph inference engine. Experiments show that GLISP achieves up to $6.53times$ and $70.77times$ speedups over existing GNN systems for training and inference tasks.
  arXiv  Detail & Related papers  (2024-01-06T02:59:24Z)
• Transferability of Graph Neural Networks using Graphon and Sampling Theories [0.0]
  Graph neural networks (GNNs) have become powerful tools for processing graph-based information in various domains. A desirable property of GNNs is transferability, where a trained network can swap in information from a different graph without retraining and retain its accuracy. We contribute to the application of graphons to GNNs by presenting an explicit two-layer graphon neural network (WNN) architecture.
  arXiv  Detail & Related papers  (2023-07-25T02:11:41Z)
• A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking [124.21408098724551]
  Large-scale graph training is a notoriously challenging problem for graph neural networks (GNNs) We present a new ensembling training manner, named EnGCN, to address the existing issues. Our proposed method has achieved new state-of-the-art (SOTA) performance on large-scale datasets.
  arXiv  Detail & Related papers  (2022-10-14T03:43:05Z)
• MentorGNN: Deriving Curriculum for Pre-Training GNNs [61.97574489259085]
  We propose an end-to-end model named MentorGNN that aims to supervise the pre-training process of GNNs across graphs. We shed new light on the problem of domain adaption on relational data (i.e., graphs) by deriving a natural and interpretable upper bound on the generalization error of the pre-trained GNNs.
  arXiv  Detail & Related papers  (2022-08-21T15:12:08Z)
• Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks [52.566735716983956]
  We propose a graph gradual pruning framework termed CGP to dynamically prune GNNs. Unlike LTH-based methods, the proposed CGP approach requires no re-training, which significantly reduces the computation costs. Our proposed strategy greatly improves both training and inference efficiency while matching or even exceeding the accuracy of existing methods.
  arXiv  Detail & Related papers  (2022-07-18T14:23:31Z)
• Learning Graph Structure from Convolutional Mixtures [119.45320143101381]
  We propose a graph convolutional relationship between the observed and latent graphs, and formulate the graph learning task as a network inverse (deconvolution) problem. In lieu of eigendecomposition-based spectral methods, we unroll and truncate proximal gradient iterations to arrive at a parameterized neural network architecture that we call a Graph Deconvolution Network (GDN) GDNs can learn a distribution of graphs in a supervised fashion, perform link prediction or edge-weight regression tasks by adapting the loss function, and they are inherently inductive.
  arXiv  Detail & Related papers  (2022-05-19T14:08:15Z)
• LSP : Acceleration and Regularization of Graph Neural Networks via Locality Sensitive Pruning of Graphs [2.4250821950628234]
  Graph Neural Networks (GNNs) have emerged as highly successful tools for graph-related tasks. Large graphs often involve many redundant components that can be removed without compromising the performance. We propose a systematic method called Locality-Sensitive Pruning (LSP) for graph pruning based on Locality-Sensitive Hashing.
  arXiv  Detail & Related papers  (2021-11-10T14:12:28Z)
• A Unified Lottery Ticket Hypothesis for Graph Neural Networks [82.31087406264437]
  We present a unified GNN sparsification (UGS) framework that simultaneously prunes the graph adjacency matrix and the model weights. We further generalize the popular lottery ticket hypothesis to GNNs for the first time, by defining a graph lottery ticket (GLT) as a pair of core sub-dataset and sparse sub-network.
  arXiv  Detail & Related papers  (2021-02-12T21:52:43Z)
• Fast Graph Attention Networks Using Effective Resistance Based Graph Sparsification [70.50751397870972]
  FastGAT is a method to make attention based GNNs lightweight by using spectral sparsification to generate an optimal pruning of the input graph. We experimentally evaluate FastGAT on several large real world graph datasets for node classification tasks.
  arXiv  Detail & Related papers  (2020-06-15T22:07:54Z)
• CoSimGNN: Towards Large-scale Graph Similarity Computation [5.17905821006887]
  Graph Neural Networks (GNNs) provide a data-driven solution for this task. Existing GNN-based methods, which either respectively embeds two graphs or deploy cross-graph interactions for whole graph pairs, are still not able to achieve competitive results. We propose the "embedding-coarsening-matching" framework CoSimGNN, which first embeds and coarsens large graphs with adaptive pooling operation and then deploys fine-grained interactions on the coarsened graphs for final similarity scores.
  arXiv  Detail & Related papers  (2020-05-14T16:33:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.