In the area of large-scale graph data representation and semi-supervised learning, deep graph-based convolutional neural networks have been widely applied. However, typical graph convolutional network (GCN) aggregates information of neighbor nodes based on binary neighborhood similarity (adjacency matrix). It treats all neighbor nodes of one node equally, which does not suppress the influence of dissimilar neighbor nodes. In this paper, we investigate GCN based on similarity matrix instead of adjacency matrix of graph nodes. Gaussian heat kernel similarity in Euclidean space is first adopted, which is named EGCN. Then biologically inspired manifold similarity is trained in reproducing kernel Hilbert space (RKHS), based on which a manifold GCN (named MGCN) is proposed for graph data representation and semi-supervised learning with four different kernel types. The proposed method is evaluated with extensive experiments on four benchmark document citation network datasets. The objective function of manifold similarity learning converges very quickly on different datasets using various kernel functions. Compared with state-of-the-art methods, our method is very competitive in terms of graph node recognition accuracy. In particular, the recognition rates of MGCN (Gaussian kernel) and MGCN (Polynomial Kernel) outperform that of typical GCN about 3.8% on Cora dataset, 3.5% on Citeseer dataset, 1.3% on Pubmed dataset and 4% on Cora_ML dataset, respectively. Although the proposed MGCN is relatively simple and easy to implement, it can discover local manifold structure by manifold similarity learning and suppress the influence of dissimilar neighbor nodes, which shows the effectiveness of the proposed MGCN.
It has been suggested that tumour‐infiltrating lymphocytes (TILs) are associated with the progression of oral squamous cell carcinoma (OSCC). However, the prognostic value of TILs is inconclusive due to the heterogeneity of immune cells within the tumour microenvironment. In this meta‐analysis, we aimed to assess the prognostic value of TILs in OSCC. The PubMed, Cochrane, Embase, Scopus and Web of Science databases were searched up to April 20, 2019, and 33 studies were ultimately included in this meta‐analysis. Our pooled meta‐analysis showed that high infiltration of CD8+ TILs, CD45RO+ TILs and CD57+ TILs favoured better overall survival (OS). However, high infiltration of CD68+ macrophages and CD163+ macrophages was associated with poor prognosis in OSCC. These findings suggest that CD8+ TILs, CD45RO+ TILs, CD57+ TILs, CD68+ macrophages and CD163+ macrophages might serve as novel prognostic factors and therapeutic targets in OSCC. 相似文献