Multi-Level Attention Pooling for Graph Neural Networks: Unifying Graph Representations with Multiple Localities

• URL: http://arxiv.org/abs/2103.01488v1
• Date: Tue, 2 Mar 2021 05:58:12 GMT
• Title: Multi-Level Attention Pooling for Graph Neural Networks: Unifying Graph Representations with Multiple Localities
• Authors: Takeshi D. Itoh and Takatomi Kubo and Kazushi Ikeda
• Abstract summary: Graph neural networks (GNNs) have been widely used to learn vector representation of graph-structured data. A potential cause is that deep GNN models tend to lose the nodes' local information through many message passing steps. We propose a multi-level attention pooling architecture to solve this so-called oversmoothing problem.
• Score: 4.142375560633827
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Graph neural networks (GNNs) have been widely used to learn vector representation of graph-structured data and achieved better task performance than conventional methods. The foundation of GNNs is the message passing procedure, which propagates the information in a node to its neighbors. Since this procedure proceeds one step per layer, the scope of the information propagation among nodes is small in the early layers, and it expands toward the later layers. The problem here is that the model performances degrade as the number of layers increases. A potential cause is that deep GNN models tend to lose the nodes' local information, which would be essential for good model performances, through many message passing steps. To solve this so-called oversmoothing problem, we propose a multi-level attention pooling (MLAP) architecture. It has an attention pooling layer for each message passing step and computes the final graph representation by unifying the layer-wise graph representations. The MLAP architecture allows models to utilize the structural information of graphs with multiple levels of localities because it preserves layer-wise information before losing them due to oversmoothing. Results of our experiments show that the MLAP architecture improves deeper models' performance in graph classification tasks compared to the baseline architectures. In addition, analyses on the layer-wise graph representations suggest that MLAP has the potential to learn graph representations with improved class discriminability by aggregating information with multiple levels of localities.

Related papers

• DA-MoE: Addressing Depth-Sensitivity in Graph-Level Analysis through Mixture of Experts [70.21017141742763]
  Graph neural networks (GNNs) are gaining popularity for processing graph-structured data. Existing methods generally use a fixed number of GNN layers to generate representations for all graphs. We propose the depth adaptive mixture of expert (DA-MoE) method, which incorporates two main improvements to GNN.
  arXiv  Detail & Related papers  (2024-11-05T11:46:27Z)
• Addressing Heterophily in Node Classification with Graph Echo State Networks [11.52174067809364]
  We address the challenges of heterophilic graphs with Graph Echo State Network (GESN) for node classification. GESN is a reservoir computing model for graphs, where node embeddings are computed by an untrained message-passing function. Our experiments show that reservoir models are able to achieve better or comparable accuracy with respect to most fully trained deep models.
  arXiv  Detail & Related papers  (2023-05-14T19:42:31Z)
• AGNN: Alternating Graph-Regularized Neural Networks to Alleviate Over-Smoothing [29.618952407794776]
  We propose an Alternating Graph-regularized Neural Network (AGNN) composed of Graph Convolutional Layer (GCL) and Graph Embedding Layer (GEL) GEL is derived from the graph-regularized optimization containing Laplacian embedding term, which can alleviate the over-smoothing problem. AGNN is evaluated via a large number of experiments including performance comparison with some multi-layer or multi-order graph neural networks.
  arXiv  Detail & Related papers  (2023-04-14T09:20:03Z)
• Building Shortcuts between Distant Nodes with Biaffine Mapping for Graph Convolutional Networks [18.160610500658183]
  We introduce Biaffine technique to improve the expressiveness of graph convolutional networks with a shallow architecture. Our method is to learn direct dependency on long-distance neighbors for nodes, with which only one-hop message passing is capable of capturing rich information for node representation.
  arXiv  Detail & Related papers  (2023-02-17T06:39:47Z)
• Gradient Gating for Deep Multi-Rate Learning on Graphs [62.25886489571097]
  We present Gradient Gating (G$2$), a novel framework for improving the performance of Graph Neural Networks (GNNs) Our framework is based on gating the output of GNN layers with a mechanism for multi-rate flow of message passing information across nodes of the underlying graph.
  arXiv  Detail & Related papers  (2022-10-02T13:19:48Z)
• ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network [72.16255675586089]
  We propose an Adaptive Curvature Exploration Hyperbolic Graph NeuralNetwork named ACE-HGNN to adaptively learn the optimal curvature according to the input graph and downstream tasks. Experiments on multiple real-world graph datasets demonstrate a significant and consistent performance improvement in model quality with competitive performance and good generalization ability.
  arXiv  Detail & Related papers  (2021-10-15T07:18:57Z)
• Graph-MLP: Node Classification without Message Passing in Graph [28.604893350871777]
  Graph Neural Network (GNN) has been demonstrated its effectiveness in dealing with non-Euclidean structural data. Recent works have mainly focused on powerful message passing modules, however, in this paper, we show that none of the message passing modules is necessary. We propose a pure multilayer-perceptron-based framework, Graph-MLP with the supervision signal leveraging graph structure.
  arXiv  Detail & Related papers  (2021-06-08T02:07:21Z)
• Hierarchical Graph Capsule Network [78.4325268572233]
  We propose hierarchical graph capsule network (HGCN) that can jointly learn node embeddings and extract graph hierarchies. To learn the hierarchical representation, HGCN characterizes the part-whole relationship between lower-level capsules (part) and higher-level capsules (whole)
  arXiv  Detail & Related papers  (2020-12-16T04:13:26Z)
• Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition [126.51241919472356]
  We design a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition. Our network is constructed by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths.
  arXiv  Detail & Related papers  (2020-11-26T14:43:04Z)
• Multi-Level Graph Convolutional Network with Automatic Graph Learning for Hyperspectral Image Classification [63.56018768401328]
  We propose a Multi-level Graph Convolutional Network (GCN) with Automatic Graph Learning method (MGCN-AGL) for HSI classification. By employing attention mechanism to characterize the importance among spatially neighboring regions, the most relevant information can be adaptively incorporated to make decisions. Our MGCN-AGL encodes the long range dependencies among image regions based on the expressive representations that have been produced at local level.
  arXiv  Detail & Related papers  (2020-09-19T09:26:20Z)
• Unsupervised Hierarchical Graph Representation Learning by Mutual Information Maximization [8.14036521415919]
  We present an unsupervised graph representation learning method, Unsupervised Hierarchical Graph Representation (UHGR) Our method focuses on maximizing mutual information between "local" and high-level "global" representations. The results show that the proposed method achieves comparable results to state-of-the-art supervised methods on several benchmarks.
  arXiv  Detail & Related papers  (2020-03-18T18:21:48Z)

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.