Cross-Representation Knowledge Transfer for Improved Sequential Recommendations
This work provides an incremental improvement in recommendation quality for users of sequential recommender systems by better integrating different types of interaction data.
This paper addresses the limitations of transformer and graph neural network models in sequential recommendation by proposing a framework that combines them. The framework simultaneously encodes structural dependencies in the interaction graph and tracks their dynamic change, consistently outperforming existing sequential and graph approaches on several open datasets.
Transformer architectures, capable of capturing sequential dependencies in the history of user interactions, have become the dominant approach in sequential recommender systems. Despite their success, such models consider sequence elements in isolation, implicitly accounting for the complex relationships between them. Graph neural networks, in contrast, explicitly model these relationships through higher order interactions but are often unable to adequately capture their evolution over time, limiting their use for predicting the next interaction. To fill this gap, we present a new framework that combines transformers and graph neural networks and aligns different representations for solving next-item prediction task. Our solution simultaneously encodes structural dependencies in the interaction graph and tracks their dynamic change. Experimental results on a number of open datasets demonstrate that the proposed framework consistently outperforms both pure sequential and graph approaches in terms of recommendation quality, as well as recent methods that combine both types of signals.