Abstract

Recently, graph convolutional neural network as an efficient and effective method has experienced significant attention and becomes the de facto method for learning node or graph representations. However, existing most methods use a fixed-order neighborhood information when integrating node representations for node classification on the graph. In this paper, we present a neighborhood adaptive graph convolutional network (NAGCN), a novel method to efficiently learn each node’s representations. Particularly, we construct a convolutional kernel abstracted from the diffusion process, named as the neighborhood adaptive kernel to more precisely learn and integrate related neighborhood node information for each node. As a result, our proposed method can learn more useful information across the relevant near and distant neighbors according to the real applications. We also adopt a threshold mechanism on the constructed kernel to better reserve the most impact neighbor vertices for each node on the graph. Besides, one learnable feature refinement process is used in the model to obtain high-level node representations with sufficient expressive power. The model is also theoretically analyzed in terms of spectral convolution and message passing algorithm. Notably, extensive experiments demonstrate that our method can achieve better performance on node classification tasks compared to other related approaches.

Highlights

  • Convolutional neural networks (CNNs) have proven remarkably successful in a variety of machine learning tasks, such as computer vision [1], natural language processing [2], and speech recognition [3]

  • We propose a neighborhood adaptive graph convolutional network to efficiently learn the representations of each node for node classification tasks

  • PERFORMANCE OF OUR neighborhood adaptive graph convolutional network (NAGCN) MODEL We evaluate the effectiveness of our proposed NAGCN model on three benchmark datasets for semi-supervised node classification tasks

Read more

Summary

INTRODUCTION

Convolutional neural networks (CNNs) have proven remarkably successful in a variety of machine learning tasks, such as computer vision [1], natural language processing [2], and speech recognition [3] It provides us an attractive and efficient architecture to extract useful features and learn meaningful representations of the tensor data in Euclidean structure. We propose a neighborhood adaptive graph convolutional network to efficiently learn the representations of each node for node classification tasks. We construct the neighborhood adaptive kernel abstracted from the diffusion process to more effectively aggregate the information of the most impact neighbor nodes, achieving feature extraction which is more conducive to the corresponding real applications. The following desirable properties of our proposed method are mainly included: (1) Our model is localized in the vertex domain since the defined neighborhood adaptive kernel reflects the information diffusion centered at each node.

RELATED WORKS
PROBLEM DEFINITION
NEIGHBORHOOD ADAPTIVE GRAPH CONVOLUTIONAL NETWORK
10: Return
SPECTRAL CONVOLUTION
MESSAGE PASSING ALGORITHM
EXPERIMENTS
DATASETS
IMPACT OF THE VARYING NUMBER OF TRAINING DATA
Findings
CONCLUSION

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.