Network Shared Data Mining Technology and Application Based on Deep Learning

In order to further improve network shared data mining effect, this paper proposes a network shared data mining technology based on deep learning, which adopts a multi-layer graph convolution network structure, and gradually expands the receptive field by stacking multiple graph convolution layers, thus capturing a wider range of neighborhood information. The adopted GCN model is based on the information aggregation mechanism of local neighborhood, and the characterization of nodes is updated layer by layer by using the feature information and topological structure of nodes. In addition to this, the adopted codec network structure includes an encoder, which is responsible for learning the compressed representations of the input data, and a decoder, which reconstructs the input data from these representations. Combined with the experimental research, it can be seen that the accuracy of the method proposed in this paper is over 90% for multi-source heterogeneous data aggregation. Moreover, compared with the existing algorithms, the data aggregation speed of this method is faster and has better data aggregation effect.