Abstract
Session-based recommendation (SBR) is a challenging task, which aims at recommending items based on anonymous behavior sequences. Almost all the existing solutions for SBR model user preference only based on the current session without exploiting the other sessions, which may contain both relevant and irrelevant item-transitions to the current session. This paper proposes a novel approach, called Global Context Enhanced Graph Neural Networks (GCE-GNN) to exploit item transitions over all sessions in a more subtle manner for better inferring the user preference of the current session. Specifically, GCE-GNN learns two levels of item embeddings from session graph and global graph, respectively: (i) Session graph, which is to learn the session-level item embedding by modeling pairwise item-transitions within the current session; and (ii) Global graph, which is to learn the global-level item embedding by modeling pairwise item-transitions over all sessions. In GCEGNN, we propose a novel global-level item representation learning
layer, which employs a session-aware attention mechanism to recursively incorporate the neighbors’ embeddings of each node on the global graph. We also design a session-level item representation learning layer, which employs a GNN on the session graph to learn session-level item embeddings within the current session. Moreover, GCE-GNN aggregates the learnt item representations in the two levels with a soft attention mechanism. Experiments on three
benchmark datasets demonstrate that GCE-GNN outperforms the state-of-the-art methods consistently
요약
1.
기존 session-based recommendation의 경우 current session을 기준으로 추천을 하게 되는데 이는 유저의 선호도와 관련있는 아이템, 관련 없는 아이템을 모두 포함하고 있다.
2.
Global Context Enhanced Graph Neural Networks (GCE-GNN)에서는 item-transition을 session 단위에서 모델링한 session graph와 global level에서 모델링한 global graph 두개를 고려하여 user preference를 만든다.
•
유저의 session에서는 relevant한 아이템과 irrelevant한 아이템이 섞여있다.
•
global level에서 item transition을 잘 뽑아내면 추천을 잘할 수 있다.
•
session graph와 global graph
•
GCE-GNN 아키텍쳐