Enhanced Soups for Graph Neural Networks

• URL: http://arxiv.org/abs/2503.11612v1
• Date: Fri, 14 Mar 2025 17:29:27 GMT
• Title: Enhanced Soups for Graph Neural Networks
• Authors: Joseph Zuber, Aishwarya Sarkar, Joseph Jennings, Ali Jannesari,
• Abstract summary: "souping" individually trained Graph Neural Networks (GNNs) can improve performance without increasing compute and memory costs during inference.<n>We introduce Learned Souping for GNNs, a gradient-descent-based souping strategy that substantially reduces time and memory overhead.<n>We also propose Partition Learned Souping, a novel partition-based variant of learned souping that significantly reduces memory usage.
• Score: 5.242305867893238
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph Neural Networks (GNN) have demonstrated state-of-the-art performance in numerous scientific and high-performance computing (HPC) applications. Recent work suggests that "souping" (combining) individually trained GNNs into a single model can improve performance without increasing compute and memory costs during inference. However, existing souping algorithms are often slow and memory-intensive, which limits their scalability. We introduce Learned Souping for GNNs, a gradient-descent-based souping strategy that substantially reduces time and memory overhead compared to existing methods. Our approach is evaluated across multiple Open Graph Benchmark (OGB) datasets and GNN architectures, achieving up to 1.2% accuracy improvement and 2.1X speedup. Additionally, we propose Partition Learned Souping, a novel partition-based variant of learned souping that significantly reduces memory usage. On the ogbn-products dataset with GraphSAGE, partition learned souping achieves a 24.5X speedup and a 76% memory reduction without compromising accuracy.

Related papers

• Distributed Graph Neural Network Inference With Just-In-Time Compilation For Industry-Scale Graphs [6.924892368183222]
  Graph neural networks (GNNs) have delivered remarkable results in various fields.<n>The rapid increase in the scale of graph data has introduced significant performance bottlenecks for GNN inference.<n>This paper introduces an innovative processing paradgim for distributed graph learning that abstracts GNNs with a new set of programming interfaces.
  arXiv  Detail & Related papers  (2025-03-08T13:26:59Z)
• FIT-GNN: Faster Inference Time for GNNs Using Coarsening [1.323700980948722]
  coarsening-based methods are used to reduce the graph into a smaller graph, resulting in faster computation.<n>Prior research has not adequately addressed the computational costs during the inference phase.<n>This paper presents a novel approach to improve the scalability of GNNs by reducing computational burden during both training and inference phases.
  arXiv  Detail & Related papers  (2024-10-19T06:27:24Z)
• Haste Makes Waste: A Simple Approach for Scaling Graph Neural Networks [37.41604955004456]
  Graph neural networks (GNNs) have demonstrated remarkable success in graph representation learning. Various sampling approaches have been proposed to scale GNNs to applications with large-scale graphs.
  arXiv  Detail & Related papers  (2024-10-07T18:29:02Z)
• Efficient Heterogeneous Graph Learning via Random Projection [58.4138636866903]
  Heterogeneous Graph Neural Networks (HGNNs) are powerful tools for deep learning on heterogeneous graphs. Recent pre-computation-based HGNNs use one-time message passing to transform a heterogeneous graph into regular-shaped tensors. We propose a hybrid pre-computation-based HGNN, named Random Projection Heterogeneous Graph Neural Network (RpHGNN)
  arXiv  Detail & Related papers  (2023-10-23T01:25:44Z)
• Cached Operator Reordering: A Unified View for Fast GNN Training [24.917363701638607]
  Graph Neural Networks (GNNs) are a powerful tool for handling structured graph data and addressing tasks such as node classification, graph classification, and clustering. However, the sparse nature of GNN computation poses new challenges for performance optimization compared to traditional deep neural networks. We address these challenges by providing a unified view of GNN computation, I/O, and memory.
  arXiv  Detail & Related papers  (2023-08-23T12:27:55Z)
• 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)
• 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)
• DistGNN: Scalable Distributed Training for Large-Scale Graph Neural Networks [58.48833325238537]
  Full-batch training on Graph Neural Networks (GNN) to learn the structure of large graphs is a critical problem that needs to scale to hundreds of compute nodes to be feasible. In this paper, we presentGNN that optimize the well-known Deep Graph Library (DGL) for full-batch training on CPU clusters. Our results on four common GNN benchmark datasets show up to 3.7x speed-up using a single CPU socket and up to 97x speed-up using 128 CPU sockets.
  arXiv  Detail & Related papers  (2021-04-14T08:46:35Z)
• Scaling Graph Neural Networks with Approximate PageRank [64.92311737049054]
  We present the PPRGo model which utilizes an efficient approximation of information diffusion in GNNs. In addition to being faster, PPRGo is inherently scalable, and can be trivially parallelized for large datasets like those found in industry settings. We show that training PPRGo and predicting labels for all nodes in this graph takes under 2 minutes on a single machine, far outpacing other baselines on the same graph.
  arXiv  Detail & Related papers  (2020-07-03T09:30:07Z)
• 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)

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.