论文标题
分数阶图神经网络
Fractional order graph neural network
论文作者
论文摘要
本文提出了分数订单图神经网络（FGNN），该图表通过近似策略进行了优化，以解决经典和分数图神经网络的局部最佳挑战，这些挑战是专门从事连接节点及其邻居及其邻居以求解非核核酸数据（例如图形）的信息的信息。同时，分数阶梯度的近似计算也克服了分数阶派生的高计算复杂性。我们进一步证明了这种近似值是可行的，并且FGNN对全局优化解决方案没有偏见。关于引用网络的广泛实验表明，当选择适当的分数顺序时，FGNN比基线模型具有很大的优势。
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.
