Next Article in Journal
A Method for Prediction of Waterlogging Economic Losses in a Subway Station Project
Previous Article in Journal
Fuzzy Clustering Methods with Rényi Relative Entropy and Cluster Size
Article

Dynamic Graph Learning for Session-Based Recommendation

Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China
*
Author to whom correspondence should be addressed.
Academic Editor: Amir Mosavi
Mathematics 2021, 9(12), 1420; https://doi.org/10.3390/math9121420
Received: 22 April 2021 / Revised: 14 June 2021 / Accepted: 15 June 2021 / Published: 19 June 2021
Session-based recommendation (SBRS) aims to make recommendations for users merely based on the ongoing session. Existing GNN-based methods achieve satisfactory performance by exploiting the pair-wise item transition pattern; however, they ignore the temporal evolution of the session graphs over different time-steps. Moreover, the widely applied cross-entropy loss with softmax in SBRS faces the serious overfitting problem. To deal with the above issues, we propose dynamic graph learning for session-based recommendation (DGL-SR). Specifically, we design a dynamic graph neural network (DGNN) to simultaneously take the graph structural information and the temporal dynamics into consideration for learning the dynamic item representations. Moreover, we propose a corrective margin softmax (CMS) to prevent overfitting in the model optimization by correcting the gradient of the negative samples. Comprehensive experiments are conducted on two benchmark datasets, that is, Diginetica and Gowalla, and the experimental results show the superiority of DGL-SR over the state-of-the-art baselines in terms of [email protected] and [email protected], especially on hitting the target item in the recommendation list. View Full-Text
Keywords: recommender systems; session-based recommendation; dynamic graph learning; graph neural networks; corrective margin softmax recommender systems; session-based recommendation; dynamic graph learning; graph neural networks; corrective margin softmax
Show Figures

Figure 1

MDPI and ACS Style

Pan, Z.; Chen, W.; Chen, H. Dynamic Graph Learning for Session-Based Recommendation. Mathematics 2021, 9, 1420. https://doi.org/10.3390/math9121420

AMA Style

Pan Z, Chen W, Chen H. Dynamic Graph Learning for Session-Based Recommendation. Mathematics. 2021; 9(12):1420. https://doi.org/10.3390/math9121420

Chicago/Turabian Style

Pan, Zhiqiang, Wanyu Chen, and Honghui Chen. 2021. "Dynamic Graph Learning for Session-Based Recommendation" Mathematics 9, no. 12: 1420. https://doi.org/10.3390/math9121420

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop