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

• URL: http://arxiv.org/abs/2309.15875v1
• Date: Wed, 27 Sep 2023 05:15:02 GMT
• Title: STAG: Enabling Low Latency and Low Staleness of GNN-based Services with Dynamic Graphs
• Abstract summary: We propose STAG, a GNN serving framework that enables low latency and low staleness of GNN-based services. Experimental results show that STAG accelerates the update phase by 1.3x90.1x, and greatly reduces staleness time with a slight increase in response latency.
• Score: 20.94927463359297
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 accordingly. However, the node representation update is too slow, resulting in either long response latency of user queries (the inference is performed after the update completes) or high staleness problem (the inference is performed based on stale data). Our in-depth analysis shows that the slow update is mainly due to neighbor explosion problem in graphs and duplicated computation. Based on such findings, we propose STAG, a GNN serving framework that enables low latency and low staleness of GNN-based services. It comprises a collaborative serving mechanism and an additivity-based incremental propagation strategy. With the collaborative serving mechanism, only part of node representations are updated during the update phase, and the final representations are calculated in the inference phase. It alleviates the neighbor explosion problem. The additivity-based incremental propagation strategy reuses intermediate data during the update phase, eliminating duplicated computation problem. Experimental results show that STAG accelerates the update phase by 1.3x~90.1x, and greatly reduces staleness time with a slight increase in response latency.

Related papers

• Spiking Heterogeneous Graph Attention Networks [17.094622281945853]
  We propose the Spiking Heterogeneous Graph Attention Networks (SpikingHAN) to reduce the computing cost without compromising the performance.<n>SpikingHAN aggregates metapath-based neighbor information using a single-layer graph convolution with shared parameters.<n>It then employs a semantic-level attention mechanism to capture the importance of different meta-paths and performs semantic aggregation.
  arXiv  Detail & Related papers  (2025-12-31T08:17:59Z)
• Asynchronous Message Passing for Addressing Oversquashing in Graph Neural Networks [21.49824162847618]
  Graph Neural Networks (GNNs) suffer from Oversquashing, which occurs when tasks require long-range interactions.<n>We propose an efficient model-agnostic framework that asynchronously updates node features, unlike traditional synchronous message passing GNNs.<n>Our framework is applied to six standard graph datasets and two long-range datasets to perform graph classification.
  arXiv  Detail & Related papers  (2025-09-08T15:03:05Z)
• Robust Graph Neural Network based on Graph Denoising [10.564653734218755]
  Graph Neural Networks (GNNs) have emerged as a notorious alternative to address learning problems dealing with non-Euclidean datasets. This work proposes a robust implementation of GNNs that explicitly accounts for the presence of perturbations in the observed topology.
  arXiv  Detail & Related papers  (2023-12-11T17:43:57Z)
• Non-backtracking Graph Neural Networks [28.206751149328216]
  We propose a non-backtracking graph neural network (NBA-GNN) that updates a message without incorporating the message from the previously visited node. We theoretically investigate how NBA-GNN alleviates the over-squashing of GNNs, and establish the impressive performance of non-backtracking updates for block recovery.
  arXiv  Detail & Related papers  (2023-10-11T12:32:13Z)
• Temporal Aggregation and Propagation Graph Neural Networks for Dynamic Representation [67.26422477327179]
  Temporal graphs exhibit dynamic interactions between nodes over continuous time. We propose a novel method of temporal graph convolution with the whole neighborhood. Our proposed TAP-GNN outperforms existing temporal graph methods by a large margin in terms of both predictive performance and online inference latency.
  arXiv  Detail & Related papers  (2023-04-15T08:17:18Z)
• $\rm A^2Q$: Aggregation-Aware Quantization for Graph Neural Networks [18.772128348519566]
  We propose the Aggregation-Aware mixed-precision Quantization ($rm A2Q$) for Graph Neural Networks (GNNs) Our method can achieve up to 11.4% and 9.5% accuracy improvements on the node-level and graph-level tasks, respectively, and up to 2x speedup on a dedicated hardware accelerator.
  arXiv  Detail & Related papers  (2023-02-01T02:54:35Z)
• Instant Graph Neural Networks for Dynamic Graphs [18.916632816065935]
  We propose Instant Graph Neural Network (InstantGNN), an incremental approach for the graph representation matrix of dynamic graphs. Our method avoids time-consuming, repetitive computations and allows instant updates on the representation and instant predictions. Our model achieves state-of-the-art accuracy while having orders-of-magnitude higher efficiency than existing methods.
  arXiv  Detail & Related papers  (2022-06-03T03:27:42Z)
• AEGNN: Asynchronous Event-based Graph Neural Networks [54.528926463775946]
  Event-based Graph Neural Networks generalize standard GNNs to process events as "evolving"-temporal graphs. AEGNNs are easily trained on synchronous inputs and can be converted to efficient, "asynchronous" networks at test time.
  arXiv  Detail & Related papers  (2022-03-31T16:21:12Z)
• Learning to Drop: Robust Graph Neural Network via Topological Denoising [50.81722989898142]
  We propose PTDNet, a parameterized topological denoising network, to improve the robustness and generalization performance of Graph Neural Networks (GNNs) PTDNet prunes task-irrelevant edges by penalizing the number of edges in the sparsified graph with parameterized networks. We show that PTDNet can improve the performance of GNNs significantly and the performance gain becomes larger for more noisy datasets.
  arXiv  Detail & Related papers  (2020-11-13T18:53:21Z)
• A Unified View on Graph Neural Networks as Graph Signal Denoising [49.980783124401555]
  Graph Neural Networks (GNNs) have risen to prominence in learning representations for graph structured data. In this work, we establish mathematically that the aggregation processes in a group of representative GNN models can be regarded as solving a graph denoising problem. We instantiate a novel GNN model, ADA-UGNN, derived from UGNN, to handle graphs with adaptive smoothness across nodes.
  arXiv  Detail & Related papers  (2020-10-05T04:57:18Z)
• 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)
• Gated Graph Recurrent Neural Networks [176.3960927323358]
  We introduce Graph Recurrent Neural Networks (GRNNs) as a general learning framework for graph processes. To address the problem of vanishing gradients, we put forward GRNNs with three different gating mechanisms: time, node and edge gates. The numerical results also show that GRNNs outperform GNNs and RNNs, highlighting the importance of taking both the temporal and graph structures of a graph process into account.
  arXiv  Detail & Related papers  (2020-02-03T22:35:14Z)

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.