Semantic Graph Neural Network with Multi-measure Learning for Semi-supervised Classification

12/04/2022
by   Junchao Lin, et al.
0

Graph Neural Networks (GNNs) have attracted increasing attention in recent years and have achieved excellent performance in semi-supervised node classification tasks. The success of most GNNs relies on one fundamental assumption, i.e., the original graph structure data is available. However, recent studies have shown that GNNs are vulnerable to the complex underlying structure of the graph, making it necessary to learn comprehensive and robust graph structures for downstream tasks, rather than relying only on the raw graph structure. In light of this, we seek to learn optimal graph structures for downstream tasks and propose a novel framework for semi-supervised classification. Specifically, based on the structural context information of graph and node representations, we encode the complex interactions in semantics and generate semantic graphs to preserve the global structure. Moreover, we develop a novel multi-measure attention layer to optimize the similarity rather than prescribing it a priori, so that the similarity can be adaptively evaluated by integrating measures. These graphs are fused and optimized together with GNN towards semi-supervised classification objective. Extensive experiments and ablation studies on six real-world datasets clearly demonstrate the effectiveness of our proposed model and the contribution of each component.

READ FULL TEXT

page 3

page 8

page 10

page 11

research
06/08/2021

NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs

Graph Neural Networks (GNNs) have achieved promising results for semi-su...
research
10/30/2020

On the Impact of Communities on Semi-supervised Classification Using Graph Neural Networks

Graph Neural Networks (GNNs) are effective in many applications. Still, ...
research
08/12/2020

Quaternion Graph Neural Networks

We consider reducing model parameters and moving beyond the Euclidean sp...
research
05/06/2022

Learning Optimal Propagation for Graph Neural Networks

Graph Neural Networks (GNNs) have achieved tremendous success in a varie...
research
10/07/2019

Graph Few-shot Learning via Knowledge Transfer

Towards the challenging problem of semi-supervised node classification, ...
research
02/07/2023

Heterophily-Aware Graph Attention Network

Graph Neural Networks (GNNs) have shown remarkable success in graph repr...
research
02/18/2022

Graph Auto-Encoder Via Neighborhood Wasserstein Reconstruction

Graph neural networks (GNNs) have drawn significant research attention r...

Please sign up or login with your details

Forgot password? Click here to reset