Aiming at the problem that the performance of the paper citation prediction method is degraded when the features are sparse， a method based on heterogeneous feature fusion is proposed， thus can use fixed-length features， citation network features and citation time series features at the same time， thus effectively improving the accuracy of the citation prediction method. Firstly， this paper defines a citation attribute network for the paper citation prediction task， and models three types of heterogeneous features. Secondly， a paper citation prediction method for heterogeneous feature fusion is proposed. The method uses the graph neural network to process fixed-length features and citation network features， uses the recurrent neural network to process citation time series features， and fuses the extracted heterogeneous features and predicts the number of citations based on multi-head attention mechanism. Experiments on large-scale real datasets show that the proposed method can effectively utilize multiple heterogeneous features and alleviate the problem of data sparsity， and its root mean square error（RMSE） is 0.31 lower than that of the best benchmark method.