SStaGCN: Simplified stacking based graph convolutional networks

11/16/2021
by   Jia Cai, et al.
7

Graph convolutional network (GCN) is a powerful model studied broadly in various graph structural data learning tasks. However, to mitigate the over-smoothing phenomenon, and deal with heterogeneous graph structural data, the design of GCN model remains a crucial issue to be investigated. In this paper, we propose a novel GCN called SStaGCN (Simplified stacking based GCN) by utilizing the ideas of stacking and aggregation, which is an adaptive general framework for tackling heterogeneous graph data. Specifically, we first use the base models of stacking to extract the node features of a graph. Subsequently, aggregation methods such as mean, attention and voting techniques are employed to further enhance the ability of node features extraction. Thereafter, the node features are considered as inputs and fed into vanilla GCN model. Furthermore, theoretical generalization bound analysis of the proposed model is explicitly given. Extensive experiments on 3 public citation networks and another 3 heterogeneous tabular data demonstrate the effectiveness and efficiency of the proposed approach over state-of-the-art GCNs. Notably, the proposed SStaGCN can efficiently mitigate the over-smoothing problem of GCN.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 7

research
12/04/2021

Multi-scale Graph Convolutional Networks with Self-Attention

Graph convolutional networks (GCNs) have achieved remarkable learning ab...
research
09/11/2021

Border-SegGCN: Improving Semantic Segmentation by Refining the Border Outline using Graph Convolutional Network

We present Border-SegGCN, a novel architecture to improve semantic segme...
research
04/09/2020

Graph Highway Networks

Graph Convolution Networks (GCN) are widely used in learning graph repre...
research
05/20/2023

Stability and Generalization of ℓ_p-Regularized Stochastic Learning for GCN

Graph convolutional networks (GCN) are viewed as one of the most popular...
research
07/03/2023

Node-weighted Graph Convolutional Network for Depression Detection in Transcribed Clinical Interviews

We propose a simple approach for weighting self-connecting edges in a Gr...
research
11/20/2019

Graph-Driven Generative Models for Heterogeneous Multi-Task Learning

We propose a novel graph-driven generative model, that unifies multiple ...
research
02/16/2022

Turn Tree into Graph: Automatic Code Review via Simplified AST Driven Graph Convolutional Network

Automatic code review (ACR), which can relieve the costs of manual inspe...

Please sign up or login with your details

Forgot password? Click here to reset