GTNet: A Tree-Based Deep Graph Learning Architecture

• URL: http://arxiv.org/abs/2204.12802v1
• Date: Wed, 27 Apr 2022 09:43:14 GMT
• Title: GTNet: A Tree-Based Deep Graph Learning Architecture
• Authors: Nan Wu, Chaofan Wang
• Abstract summary: We propose a deep graph learning architecture with a new general message passing scheme that originates from the tree representation of graphs. Two graph representation learning models are proposed within this GTNet architecture - Graph Tree Attention Network (GTAN) and Graph Tree Convolution Network (GTCN)
• Score: 8.50892442127182
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose Graph Tree Networks (GTNets), a deep graph learning architecture with a new general message passing scheme that originates from the tree representation of graphs. In the tree representation, messages propagate upward from the leaf nodes to the root node, and each node preserves its initial information prior to receiving information from its child nodes (neighbors). We formulate a general propagation rule following the nature of message passing in the tree to update a node's feature by aggregating its initial feature and its neighbor nodes' updated features. Two graph representation learning models are proposed within this GTNet architecture - Graph Tree Attention Network (GTAN) and Graph Tree Convolution Network (GTCN), with experimentally demonstrated state-of-the-art performance on several popular benchmark datasets. Unlike the vanilla Graph Attention Network (GAT) and Graph Convolution Network (GCN) which have the "over-smoothing" issue, the proposed GTAN and GTCN models can go deep as demonstrated by comprehensive experiments and rigorous theoretical analysis.

Related papers

• Saliency-Aware Regularized Graph Neural Network [39.82009838086267]
  We propose the Saliency-Aware Regularized Graph Neural Network (SAR-GNN) for graph classification. We first estimate the global node saliency by measuring the semantic similarity between the compact graph representation and node features. Then the learned saliency distribution is leveraged to regularize the neighborhood aggregation of the backbone.
  arXiv  Detail & Related papers  (2024-01-01T13:44:16Z)
• SAILOR: Structural Augmentation Based Tail Node Representation Learning [49.19653803667422]
  Graph Neural Networks (GNNs) have achieved state-of-the-art performance in representation learning for graphs recently. Most of the graphs in real-world scenarios follow a long-tailed distribution on their node degrees, that is, a vast majority of the nodes in the graph are tail nodes with only a few connected edges. We propose a general Structural Augmentation based taIL nOde Representation learning framework, dubbed as SAILOR, which can jointly learn to augment the graph structure and extract more informative representations for tail nodes.
  arXiv  Detail & Related papers  (2023-08-13T16:04:03Z)
• TREE-G: Decision Trees Contesting Graph Neural Networks [33.364191419692105]
  TREE-G modifies standard decision trees, by introducing a novel split function that is specialized for graph data. We show that TREE-G consistently outperforms other tree-based models and often outperforms other graph-learning algorithms such as Graph Neural Networks (GNNs) and Graph Kernels.
  arXiv  Detail & Related papers  (2022-07-06T15:53:17Z)
• Graph Tree Neural Networks [0.43012765978447565]
  Graph tree neural networks (GTNNs) are designed to solve the problems of existing networks by analyzing the structure of human neural networks. In GTNNs, information units are related to the form of a graph and then they become a bigger unit of information again and have a relationship with other information units.
  arXiv  Detail & Related papers  (2021-10-31T07:58:00Z)
• Reasoning Graph Networks for Kinship Verification: from Star-shaped to Hierarchical [85.0376670244522]
  We investigate the problem of facial kinship verification by learning hierarchical reasoning graph networks. We develop a Star-shaped Reasoning Graph Network (S-RGN) to exploit more powerful and flexible capacity. We also develop a Hierarchical Reasoning Graph Network (H-RGN) to exploit more powerful and flexible capacity.
  arXiv  Detail & Related papers  (2021-09-06T03:16:56Z)
• Neural Trees for Learning on Graphs [19.05038106825347]
  Graph Neural Networks (GNNs) have emerged as a flexible and powerful approach for learning over graphs. We propose a new GNN architecture -- the Neural Tree. We show that the neural tree architecture can approximate any smooth probability distribution function over an undirected graph.
  arXiv  Detail & Related papers  (2021-05-15T17:08:20Z)
• GraphSVX: Shapley Value Explanations for Graph Neural Networks [81.83769974301995]
  Graph Neural Networks (GNNs) achieve significant performance for various learning tasks on geometric data. In this paper, we propose a unified framework satisfied by most existing GNN explainers. We introduce GraphSVX, a post hoc local model-agnostic explanation method specifically designed for GNNs.
  arXiv  Detail & Related papers  (2021-04-18T10:40:37Z)
• SPAGAN: Shortest Path Graph Attention Network [187.75441278910708]
  Graph convolutional networks (GCN) have recently demonstrated their potential in analyzing non-grid structure data that can be represented as graphs. We propose a novel GCN model, which we term as Shortest Path Graph Attention Network (SPAGAN)
  arXiv  Detail & Related papers  (2021-01-10T03:18:34Z)
• CatGCN: Graph Convolutional Networks with Categorical Node Features [99.555850712725]
  CatGCN is tailored for graph learning when the node features are categorical. We train CatGCN in an end-to-end fashion and demonstrate it on semi-supervised node classification.
  arXiv  Detail & Related papers  (2020-09-11T09:25:17Z)
• TreeRNN: Topology-Preserving Deep GraphEmbedding and Learning [24.04035265351755]
  We study the methods to transfer the graphs into trees so that explicit orders are learned to direct the feature integration from local to global. To best learn the patterns from the graph-tree-images, we propose TreeRNN, a 2D RNN architecture that recurrently integrates the image pixels by rows and columns to help classify the graph categories.
  arXiv  Detail & Related papers  (2020-06-21T15:22:24Z)
• Graph Inference Learning for Semi-supervised Classification [50.55765399527556]
  We propose a Graph Inference Learning framework to boost the performance of semi-supervised node classification. For learning the inference process, we introduce meta-optimization on structure relations from training nodes to validation nodes. Comprehensive evaluations on four benchmark datasets demonstrate the superiority of our proposed GIL when compared against state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-01-17T02:52:30Z)

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.