Fractional order graph neural network

Abstract

This paper proposes fractional order graph neural networks (FGNNs), optimized by the approximation strategy to address the challenges of local optimum of classic and fractional graph neural networks which are specialised at aggregating information from the feature and adjacent matrices of connected nodes and their neighbours to solve learning tasks on non-Euclidean data such as graphs. Meanwhile the approximate calculation of fractional order gradients also overcomes the high computational complexity of fractional order derivations. We further prove that such an approximation is feasible and the FGNN is unbiased towards global optimization solution. Extensive experiments on citation networks show that FGNN achieves great advantage over baseline models when selected appropriate fractional order.

arXiv commentThere are serious mistakes in the article and it needs to be retracted and corrected

References in corpus (11)

• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• On the difficulty of training Recurrent Neural Networks
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• Deep Convolutional Networks on Graph-Structured Data
• Learning Combinatorial Optimization Algorithms over Graphs
• Learning Convolutional Neural Networks for Graphs
• Graph networks as learnable physics engines for inference and control
• Robust Spatial Filtering with Graph Convolutional Neural Networks
• Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach
• Fractional derivative of composite functions: exact results and physical applications