This investigation tries to determine if, for highly visible journals, namely Nature, Science and Cell, articles with a short editorial delay time generally, receive more citations than those with a long editorial delay. Based on data for the period from 2005 to 2009, it is found that there is a clear, although statistically weak, tendency for an inverse relation between editorial delay time and number of received citations.

No abstract

Graph neural networks (GNNs) have shown great power in learning on graphs. However, it is still a challenge for GNNs to model information faraway from the source node. The ability to preserve global information can enhance graph representation and hence improve classification precision. In the paper, we propose a new learning framework named G-GNN (Global information for GNN) to address the challenge. First, the global structure and global attribute features of each node are obtained via unsupervised pre-training, and those global features preserve the global information associated with the node. Then, using the pre-trained global features and the raw attributes of the graph, a set of parallel kernel GNNs is used to learn different aspects from these heterogeneous features. Any general GNN can be used as a kernal and easily obtain the ability of preserving global information, without having to alter their own algorithms. Extensive experiments have shown that state-of-the-art models, e.g., GCN, GAT, Graphsage and APPNP, can achieve improvement with G-GNN on three standard evaluation datasets. Specially, we establish new benchmark precision records on Cora (84.31%) and Pubmed (80.95%) when learning on attributed graphs.

No abstract

We propose a new method for computing the bibliographic coupling strength between two documents. This new method is based on the TF-IDF formula from the field of information retrieval. It is shown that this formula is a valid alternative for the original formula introduced by Kessler and is, from a probabilistic point of view, a correction of the Vladutz-Cook formula. We further define a cosine based similarity formula generalizing the Sen-Gan coupling angle formula.