Graph Decipher: A transparent dual-attention graph neural network to understand the message-passing mechanism for the node classification

• URL: http://arxiv.org/abs/2201.01381v1
• Date: Tue, 4 Jan 2022 23:24:00 GMT
• Title: Graph Decipher: A transparent dual-attention graph neural network to understand the message-passing mechanism for the node classification
• Authors: Yan Pang, Chao Liu
• Abstract summary: We propose a new transparent network called Graph Decipher to investigate the message-passing mechanism. Our algorithm achieves state-of-the-art performance while imposing a substantially lower burden under the node classification task.
• Score: 2.0047096160313456
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph neural networks can be effectively applied to find solutions for many real-world problems across widely diverse fields. The success of graph neural networks is linked to the message-passing mechanism on the graph, however, the message-aggregating behavior is still not entirely clear in most algorithms. To improve functionality, we propose a new transparent network called Graph Decipher to investigate the message-passing mechanism by prioritizing in two main components: the graph structure and node attributes, at the graph, feature, and global levels on a graph under the node classification task. However, the computation burden now becomes the most significant issue because the relevance of both graph structure and node attributes are computed on a graph. In order to solve this issue, only relevant representative node attributes are extracted by graph feature filters, allowing calculations to be performed in a category-oriented manner. Experiments on seven datasets show that Graph Decipher achieves state-of-the-art performance while imposing a substantially lower computation burden under the node classification task. Additionally, since our algorithm has the ability to explore the representative node attributes by category, it is utilized to alleviate the imbalanced node classification problem on multi-class graph datasets.

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)
• NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification [70.51126383984555]
  We introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes. The efficient computation is enabled by a kernerlized Gumbel-Softmax operator. Experiments demonstrate the promising efficacy of the method in various tasks including node classification on graphs.
  arXiv  Detail & Related papers  (2023-06-14T09:21:15Z)
• Edge but not Least: Cross-View Graph Pooling [76.71497833616024]
  This paper presents a cross-view graph pooling (Co-Pooling) method to better exploit crucial graph structure information. Through cross-view interaction, edge-view pooling and node-view pooling seamlessly reinforce each other to learn more informative graph-level representations.
  arXiv  Detail & Related papers  (2021-09-24T08:01:23Z)
• Accurate Learning of Graph Representations with Graph Multiset Pooling [45.72542969364438]
  We propose a Graph Multiset Transformer (GMT) that captures the interaction between nodes according to their structural dependencies. Our experimental results show that GMT significantly outperforms state-of-the-art graph pooling methods on graph classification benchmarks.
  arXiv  Detail & Related papers  (2021-02-23T07:45:58Z)
• Co-embedding of Nodes and Edges with Graph Neural Networks [13.020745622327894]
  Graph embedding is a way to transform and encode the data structure in high dimensional and non-Euclidean feature space. CensNet is a general graph embedding framework, which embeds both nodes and edges to a latent feature space. Our approach achieves or matches the state-of-the-art performance in four graph learning tasks.
  arXiv  Detail & Related papers  (2020-10-25T22:39:31Z)
• Line Graph Neural Networks for Link Prediction [71.00689542259052]
  We consider the graph link prediction task, which is a classic graph analytical problem with many real-world applications. In this formalism, a link prediction problem is converted to a graph classification task. We propose to seek a radically different and novel path by making use of the line graphs in graph theory. In particular, each node in a line graph corresponds to a unique edge in the original graph. Therefore, link prediction problems in the original graph can be equivalently solved as a node classification problem in its corresponding line graph, instead of a graph classification task.
  arXiv  Detail & Related papers  (2020-10-20T05:54:31Z)
• Robust Hierarchical Graph Classification with Subgraph Attention [18.7475578342125]
  We introduce the concept of subgraph attention for graphs. We propose a graph classification algorithm called SubGattPool. We show that SubGattPool is able to improve the state-of-the-art or remains competitive on multiple publicly available graph classification datasets.
  arXiv  Detail & Related papers  (2020-07-19T10:03:06Z)
• Towards Deeper Graph Neural Networks [63.46470695525957]
  Graph convolutions perform neighborhood aggregation and represent one of the most important graph operations. Several recent studies attribute this performance deterioration to the over-smoothing issue. We propose Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields.
  arXiv  Detail & Related papers  (2020-07-18T01:11:14Z)
• Graph Pooling with Node Proximity for Hierarchical Representation Learning [80.62181998314547]
  We propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology. Results show that the proposed graph pooling strategy is able to achieve state-of-the-art performance on a collection of public graph classification benchmark datasets.
  arXiv  Detail & Related papers  (2020-06-19T13:09:44Z)
• Structure-Feature based Graph Self-adaptive Pooling [65.4188800835203]
  We propose a novel graph self-adaptive pooling method to deal with graph data. Our method is effective in graph classification and outperforms state-of-the-art graph pooling methods.
  arXiv  Detail & Related papers  (2020-01-30T13:58:49Z)

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.