Graph wavelet neural network exerts a powerful learning ability in the assortative network where most of adjacent nodes have the same label as the target node. However, it doesn't perform well in the disassortative network where most of adjacent nodes have different label than the target node. So graph wavelet neural network cannot extract the most useful information based on different types of networks. On the one hand, as a low-pass filter, graph wavelet neural network only obtains the commonality of the same label nodes, it is not capable of obtaining the difference of different label nodes. On the other hand, graph wavelet neural network only aggregates neighbor nodes so that it can't obtain information of nodes which have similar feature with the target node and are far from the target node. To solve the above problems, we propose the GWNN-HF model, which can effectively adapt to different types of networks and get a better node representation. Specifically speaking, firstly, we design low-pass filter and high-pass filter convolution kernels to get low-pass and high-pass signals and then use adaptive fusion method to fuse them, which effectively get commonality of same label nodes and difference of different label nodes. Secondly, we use the Relaxed Minimum-Spanning Tree algorithm to construct a feature correlation graph and use an attention mechanism to fuse the original graph and feature correlation graph representation. Extensive experiments on benchmark datasets clearly indicates that GWNN-HF behaves better than the state-of-the-art GNNs.