Adaptive graph convolutional collaboration networks for semi-supervised classification

-order (layer) neighborhood samples. Existing GCNs variants rely heavily on the -th layer semantic features, AGCCNs make the learned deep semantic features contain richer and more robust semantic information. What is more, our proposed AGCCNs can aggregate the appropriate -order neighborhood information for each sample, which can relieve the oversmoothing issue of traditional GCNs and better generalize shallow GCNs to more deep layers. Abundant experimental results on several popular datasets demonstrate the superiority of our proposed AGCCNs compared with traditional GCNs.