IC-GAR: item co-occurrence graph augmented session-based recommendation

Tajuddeen, Gwadabe,; Ying, Liu

doi:10.1007/s00521-021-06859-x

Cited by 10 publications

(2 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pan et al [18] designed the DGNN method in which the graph structure and the temporal dynamics were considered for learning the dynamic item embeddings. To learn both sequential and non-sequential item transitions, Gwadabe et al [8] proposed the IC-GAR method to capture the complex transitions between items in the session. Wang et al [25] presented the SGNN method which can model user's behaviors from spatial and temporal perspectives.…”

Section: Session-based Recommendationsmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Context-Embedded Hypergraph Convolutional Network for Session-based Recommendation

Zhao

Cao²,

Lv³

et al. 2023

ITC

View full text Add to dashboard Cite

The graph neural network (GNN) based approaches have attracted more and more attention in session-based recommendation tasks. However, most of the existing methods do not fully take advantage of context information in session when capturing user’s interest, and the research on context adaptation is even less. Furthermore, hypergraph has potential to express complex relations among items, but it has remained unexplored. Therefore, this paper proposes an adaptive context-embedded hypergraph convolutional network (AC-HCN) for session-based recommendation. At first, the data of sessions is constructed as session hypergraph. Then, the representation of each item in session hypergraph is learned using an adaptive context-embedded hypergraph convolution. In the convolution, different types of context information from both current item itself and the item’s neighborhoods are adaptively integrated into the representation updating of current item. Meanwhile, an adaptive transformation function is employed to effectively eliminate the effects of irrelevant items. Then, the learned item representations are combined with time interval embeddings and reversed position embeddings to fully reflect time interval information and sequential information between items in session. Finally, based on learned item representations in session, a soft attention mechanism is used to obtain user’s interest, and then a recommendation list is given. Extensive experiments on the real-world datasets show that the proposed model has significantly improvement compared with the state-of-arts methods.

show abstract

Section: Session-based Recommendationsmentioning

confidence: 99%

“…In recent years, a lot of research achievements using deep learning have been made in SBR. Among them, approaches based on Recurrent Neural Networks (RNNs) [10,27,39] and approaches based on Graph Neural Networks (GNNs) [8,28,30] have shown great performance.…”

Section: Introductionmentioning

confidence: 99%