Semantic-Enhanced Variational Graph Autoencoder for Movie Recommendation: An Innovative Approach Integrating Plot Summary Information and Contrastive Learning Strategy

This study introduces a novel movie recommender system utilizing a Semantic-Enhanced Variational Graph Autoencoder for Movie Recommendation (SeVGAER) architecture. The system harnesses additional information from movie plot summaries scraped from the internet, transformed into semantic vectors via a large language model. These vectors serve as supplementary features for movie nodes in the SeVGAER-based recommender. The system incorporates an encoder-decoder structure, operating on a user-movie bipartite graph, and employs GraphSAGE convolutional layers with modified aggregators as the encoder to extract latent representations of the nodes, and a Multi-Layer Perceptron (MLP) as the decoder to predict ratings with additional graph-based features. To address overfitting and improve model generalization, a novel training strategy is introduced. We employ a random data splitting approach, dividing the dataset into two halves for each training instance. The model then generates outputs on each half of the data, and a new loss function is introduced to ensure consistency between these two outputs, a strategy that can be seen as a form of contrastive learning. The model’s performance is optimized using a combination of this new contrastive loss, graph reconstruction loss, and KL divergence loss. Experiments conducted on the Movielens100k dataset demonstrate the effectiveness of this approach in enhancing movie recommendation performance