KEYWORDS: Neural networks, Data modeling, Performance modeling, Matrices, Systems modeling, Data hiding, Process modeling, Modeling, Control systems, Stochastic processes
In order to solve the problem that existing session recommendation methods ignore the temporal relationship between items and do not consider the correlation between the items of interest and all items, which leads to poor recommendation results. A novel session recommendation model based on Graph Neural Network (GNN), Long- and Short-Term Memory network (LSTM) and attention mechanism is proposed. The GNN and LSTM are used to capture the complex dependencies and temporal relationships between items to obtain item embeddings; the global embeddings are generated by combining multi-headed attention and soft attention to accurately represent global preferences; the interest attention mechanism is introduced to generate interest embeddings to activate interest item relevance; finally, the current embeddings are combined to obtain the final session representation and predict the next click. The model is compared with the existing benchmark model on three public datasets and the results are all improved, which proves that the proposed method is very effective.
Sequential recommendation systems exploit the user's historical item sequences to predict their next actions. Recently, dynamic graph-based methods have been studied and achieved excellent performance for recommendation. They capture dynamic collaborative signals between different user sequences by stacking multiple network layer with attention mechanism to solve insufficient interest mining problem caused by use a single user’s sequence. In online platforms, recorded user behavior data may contain noise, and stacking multiple attention network is easy to aggravate the effects of noise. In this paper, we propose Filter-enhance Temporal Graph Neural Network for Continuous-Time Sequential Recommendation (FTGRec), which connects the related interactions of different user by dynamic graph and design a module combining Fourier transform and attention mechanism to filter the noise data, to predict the order pattern of users better. Empirical results on three datasets indicate FTGRec outperforms other comparative methods.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.