WaveGAS: Waveform Relaxation for Scaling Graph Neural Networks

• URL: http://arxiv.org/abs/2502.19986v1
• Date: Thu, 27 Feb 2025 11:10:42 GMT
• Title: WaveGAS: Waveform Relaxation for Scaling Graph Neural Networks
• Authors: Jana Vatter, Mykhaylo Zayats, Marcos Martínez Galindo, Vanessa López, Ruben Mayer, Hans-Arno Jacobsen, Hoang Thanh Lam,
• Abstract summary: GNNAutoScale (GAS) uses graph partitioning to enable training under constrained GPU memory.<n>Gas stores historical embedding vectors, which are retrieved from one-hop neighbors in other partitions, ensuring critical information is captured across partition boundaries.<n>The historical embeddings which come from the previous training are stale compared to the GAS estimated embeddings, resulting in approximation errors of the training algorithm.<n>We propose two enhancements: first, WaveGAS, inspired by waveform relaxation, performs multiple forward passes within GAS before the backward pass, refining the approximation of historical embeddings and gradients to improve accuracy; second, a gradient-tracking method
• Score: 13.223473148178906
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the ever-growing size of real-world graphs, numerous techniques to overcome resource limitations when training Graph Neural Networks (GNNs) have been developed. One such approach, GNNAutoScale (GAS), uses graph partitioning to enable training under constrained GPU memory. GAS also stores historical embedding vectors, which are retrieved from one-hop neighbors in other partitions, ensuring critical information is captured across partition boundaries. The historical embeddings which come from the previous training iteration are stale compared to the GAS estimated embeddings, resulting in approximation errors of the training algorithm. Furthermore, these errors accumulate over multiple layers, leading to suboptimal node embeddings. To address this shortcoming, we propose two enhancements: first, WaveGAS, inspired by waveform relaxation, performs multiple forward passes within GAS before the backward pass, refining the approximation of historical embeddings and gradients to improve accuracy; second, a gradient-tracking method that stores and utilizes more accurate historical gradients during training. Empirical results show that WaveGAS enhances GAS and achieves better accuracy, even outperforming methods that train on full graphs, thanks to its robust estimation of node embeddings.

Related papers

• Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs [9.21955649907066]
  Pre-propagation GNNs represent a new class of models that decouple feature propagation from training through pre-processing. This paper provides a comprehensive characterization of PP-GNNs, comparing them with graph-sampling-based methods in training efficiency, scalability, and accuracy. We propose optimized data loading schemes and tailored training methods that improve PP-GNN training throughput by an average of 15$times$ over the PP-GNN baselines.
  arXiv  Detail & Related papers  (2025-04-17T18:20:40Z)
• Fast and Slow Gradient Approximation for Binary Neural Network Optimization [11.064044986709733]
  hypernetwork based methods utilize neural networks to learn the gradients of non-differentiable quantization functions.<n>We propose a Historical Gradient Storage (HGS) module, which models the historical gradient sequence to generate the first-order momentum required for optimization.<n>We also introduce Layer Recognition Embeddings (LRE) into the hypernetwork, facilitating the generation of layer-specific fine gradients.
  arXiv  Detail & Related papers  (2024-12-16T13:48:40Z)
• RobGC: Towards Robust Graph Condensation [61.259453496191696]
  Graph neural networks (GNNs) have attracted widespread attention for their impressive capability of graph representation learning. However, the increasing prevalence of large-scale graphs presents a significant challenge for GNN training due to their computational demands. We propose graph condensation (GC) to generate an informative compact graph that enables efficient training of GNNs while retaining performance.
  arXiv  Detail & Related papers  (2024-06-19T04:14:57Z)
• Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness [80.87683145376305]
  Graph Neural Networks (GNNs) excel in various graph learning tasks but face computational challenges when applied to large-scale graphs. We propose Graph Sparse Training ( GST), which dynamically manipulates sparsity at the data level. GST produces a sparse graph with maximum topological integrity and no performance degradation.
  arXiv  Detail & Related papers  (2024-02-02T09:10:35Z)
• Learning Large Graph Property Prediction via Graph Segment Training [61.344814074335304]
  We propose a general framework that allows learning large graph property prediction with a constant memory footprint. We refine the GST paradigm by introducing a historical embedding table to efficiently obtain embeddings for segments not sampled for backpropagation. Our experiments show that GST-EFD is both memory-efficient and fast, while offering a slight boost on test accuracy over a typical full graph training regime.
  arXiv  Detail & Related papers  (2023-05-21T02:53:25Z)
• 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)
• BGL: GPU-Efficient GNN Training by Optimizing Graph Data I/O and Preprocessing [0.0]
  Graph neural networks (GNNs) have extended the success of deep neural networks (DNNs) to non-Euclidean graph data. Existing systems are inefficient to train large graphs with billions of nodes and edges with GPUs. This paper proposes BGL, a distributed GNN training system designed to address the bottlenecks with a few key ideas.
  arXiv  Detail & Related papers  (2021-12-16T00:37:37Z)
• GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings [51.82434518719011]
  GNNAutoScale (GAS) is a framework for scaling arbitrary message-passing GNNs to large graphs. Gas prunes entire sub-trees of the computation graph by utilizing historical embeddings from prior training iterations. Gas reaches state-of-the-art performance on large-scale graphs.
  arXiv  Detail & Related papers  (2021-06-10T09:26:56Z)

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.