Graph Structural-topic Neural Network

06/25/2020
by   Qingqing Long, et al.
0

Graph Convolutional Networks (GCNs) achieved tremendous success by effectively gathering local features for nodes. However, commonly do GCNs focus more on node features but less on graph structures within the neighborhood, especially higher-order structural patterns. However, such local structural patterns are shown to be indicative of node properties in numerous fields. In addition, it is not just single patterns, but the distribution over all these patterns matter, because networks are complex and the neighborhood of each node consists of a mixture of various nodes and structural patterns. Correspondingly, in this paper, we propose Graph Structural-topic Neural Network, abbreviated GraphSTONE, a GCN model that utilizes topic models of graphs, such that the structural topics capture indicative graph structures broadly from a probabilistic aspect rather than merely a few structures. Specifically, we build topic models upon graphs using anonymous walks and Graph Anchor LDA, an LDA variant that selects significant structural patterns first, so as to alleviate the complexity and generate structural topics efficiently. In addition, we design multi-view GCNs to unify node features and structural topic features and utilize structural topics to guide the aggregation. We evaluate our model through both quantitative and qualitative experiments, where our model exhibits promising performance, high efficiency, and clear interpretability.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 7

page 8

page 9

research
11/18/2019

GraLSP: Graph Neural Networks with Local Structural Patterns

It is not until recently that graph neural networks (GNNs) are adopted t...
research
11/15/2022

Neighborhood Convolutional Network: A New Paradigm of Graph Neural Networks for Node Classification

The decoupled Graph Convolutional Network (GCN), a recent development of...
research
12/09/2022

Multi-view Graph Convolutional Networks with Differentiable Node Selection

Multi-view data containing complementary and consensus information can f...
research
05/31/2018

Fusion Graph Convolutional Networks

Semi-supervised node classification involves learning to classify unlabe...
research
10/12/2020

Locality Preserving Dense Graph Convolutional Networks with Graph Context-Aware Node Representations

Graph convolutional networks (GCNs) have been widely used for representa...
research
01/14/2020

Recovering the Structural Observability of Composite Networks via Cartesian Product

Observability is a fundamental concept in system inference and estimatio...
research
01/23/2020

Leveraging Neighborhood Summaries for Efficient RDF Queries on RDBMS

Using structural informations to summarize graph-structured RDF data is ...

Please sign up or login with your details

Forgot password? Click here to reset