A Study of User-item Graph Neural Network Recommendation Based on GCCGAT-LSTM

Abstract

To solve the problem of high root mean square error (RMSE) caused by the Graph Convolution with Graph Attention Network for Matrix Completion (GCGAT), which cannot fully utilize the node's feature information and temporal information. In this paper, we propose an LSTM-based GCGAT algorithm (GCGAT based on LSTM, GCGAT-LSTM) to solve this problem: the linear processing part of the encoder in GCGAT is replaced by long short-term memory algorithm (LSTM). Two LSTM layers are used to process user's and item's feature information separately, named GCGAT -LSTM. This paper conducted several experiments on MovieLens-100K and MovieLens-1M datasets. The experimental results show that GCGAT -LSTM performs better than the GCGAT algorithm, effectively improving the performance of GCGAT and making more accurate recommendations. Compared with the RMSE in the previous GCGAT algorithm, the RMSE of GCGAT-LSTM is reduced by about 0.03 on both datasets. Therefore, the GCGAT-LSTM method proposed in this paper can better use node's feature information and temporal information to make more accurate predictions and thus obtain better recommendation results. However, the GCGAT-LSTM also has some limitations: the LSTM requires sequential processing over time and therefore has low efficiency and high time complexity for the input sequence.