Analyzing the Performance of Graph Neural Networks with Pipe Parallelism

• URL: http://arxiv.org/abs/2012.10840v2
• Date: Mon, 5 Apr 2021 16:59:33 GMT
• Title: Analyzing the Performance of Graph Neural Networks with Pipe Parallelism
• Authors: Matthew T. Dearing, Xiaoyan Wang
• Abstract summary: We focus on Graph Neural Networks (GNNs) that have found great success in tasks such as node or edge classification and link prediction. New approaches for processing larger networks are needed to advance graph techniques. We study how GNNs could be parallelized using existing tools and frameworks that are known to be successful in the deep learning community.
• Score: 2.269587850533721
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many interesting datasets ubiquitous in machine learning and deep learning can be described via graphs. As the scale and complexity of graph-structured datasets increase, such as in expansive social networks, protein folding, chemical interaction networks, and material phase transitions, improving the efficiency of the machine learning techniques applied to these is crucial. In this study, we focus on Graph Neural Networks (GNN) that have found great success in tasks such as node or edge classification and link prediction. However, standard GNN models have scaling limits due to necessary recursive calculations performed through dense graph relationships that lead to memory and runtime bottlenecks. While new approaches for processing larger networks are needed to advance graph techniques, and several have been proposed, we study how GNNs could be parallelized using existing tools and frameworks that are known to be successful in the deep learning community. In particular, we investigate applying pipeline parallelism to GNN models with GPipe, introduced by Google in 2018.

Related papers

• TANGNN: a Concise, Scalable and Effective Graph Neural Networks with Top-m Attention Mechanism for Graph Representation Learning [7.879217146851148]
  We propose an innovative Graph Neural Network (GNN) architecture that integrates a Top-m attention mechanism aggregation component and a neighborhood aggregation component. To assess the effectiveness of our proposed model, we have applied it to citation sentiment prediction, a novel task previously unexplored in the GNN field.
  arXiv  Detail & Related papers  (2024-11-23T05:31:25Z)
• Graph Coordinates and Conventional Neural Networks -- An Alternative for Graph Neural Networks [0.10923877073891444]
  We propose Topology Coordinate Neural Network (TCNN) and Directional Virtual Coordinate Neural Network (DVCNN) as novel alternatives to message passing GNNs. TCNN and DVCNN achieve competitive or superior performance to message passing GNNs. Our work expands the toolbox of techniques for graph-based machine learning.
  arXiv  Detail & Related papers  (2023-12-03T10:14:10Z)
• 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)
• Automatic Relation-aware Graph Network Proliferation [182.30735195376792]
  We propose Automatic Relation-aware Graph Network Proliferation (ARGNP) for efficiently searching GNNs. These operations can extract hierarchical node/relational information and provide anisotropic guidance for message passing on a graph. Experiments on six datasets for four graph learning tasks demonstrate that GNNs produced by our method are superior to the current state-of-the-art hand-crafted and search-based GNNs.
  arXiv  Detail & Related papers  (2022-05-31T10:38:04Z)
• Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency Analysis [28.464210819376593]
  Graph neural networks (GNNs) are among the most powerful tools in deep learning. They routinely solve complex problems on unstructured networks, such as node classification, graph classification, or link prediction, with high accuracy. However, both inference and training of GNNs are complex, and they uniquely combine the features of irregular graph processing with dense and regular computations. This complexity makes it very challenging to execute GNNs efficiently on modern massively parallel architectures.
  arXiv  Detail & Related papers  (2022-05-19T17:11:45Z)
• Overcoming Oversmoothness in Graph Convolutional Networks via Hybrid Scattering Networks [11.857894213975644]
  We propose a hybrid graph neural network (GNN) framework that combines traditional GCN filters with band-pass filters defined via the geometric scattering transform. Our theoretical results establish the complementary benefits of the scattering filters to leverage structural information from the graph, while our experiments show the benefits of our method on various learning tasks.
  arXiv  Detail & Related papers  (2022-01-22T00:47:41Z)
• Increase and Conquer: Training Graph Neural Networks on Growing Graphs [116.03137405192356]
  We consider the problem of learning a graphon neural network (WNN) by training GNNs on graphs sampled Bernoulli from the graphon. Inspired by these results, we propose an algorithm to learn GNNs on large-scale graphs that, starting from a moderate number of nodes, successively increases the size of the graph during training.
  arXiv  Detail & Related papers  (2021-06-07T15:05:59Z)
• Hierarchical Message-Passing Graph Neural Networks [12.207978823927386]
  We propose a novel Hierarchical Message-passing Graph Neural Networks framework. Key idea is generating a hierarchical structure that re-organises all nodes in a flat graph into multi-level super graphs. We present the first model to implement this framework, termed Hierarchical Community-aware Graph Neural Network (HC-GNN)
  arXiv  Detail & Related papers  (2020-09-08T13:11:07Z)
• Binarized Graph Neural Network [65.20589262811677]
  We develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters. Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches. Experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space.
  arXiv  Detail & Related papers  (2020-04-19T09:43:14Z)
• Geometrically Principled Connections in Graph Neural Networks [66.51286736506658]
  We argue geometry should remain the primary driving force behind innovation in the emerging field of geometric deep learning. We relate graph neural networks to widely successful computer graphics and data approximation models: radial basis functions (RBFs) We introduce affine skip connections, a novel building block formed by combining a fully connected layer with any graph convolution operator.
  arXiv  Detail & Related papers  (2020-04-06T13:25:46Z)
• Graphs, Convolutions, and Neural Networks: From Graph Filters to Graph Neural Networks [183.97265247061847]
  We leverage graph signal processing to characterize the representation space of graph neural networks (GNNs) We discuss the role of graph convolutional filters in GNNs and show that any architecture built with such filters has the fundamental properties of permutation equivariance and stability to changes in the topology. We also study the use of GNNs in recommender systems and learning decentralized controllers for robot swarms.
  arXiv  Detail & Related papers  (2020-03-08T13:02:15Z)

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.