Session-based Recommendation via Contrastive Learning on Heterogeneous Graph. Abstract: In this work, we propose a novel session-based recommendation model ...

In this work, we propose a novel session-based recommendation model which can fully leverage the intriguing relationships among items. Firstly, a heterogeneous ...

Contrastive Learning on Heterogeneous Graph (CLHG) for session-based recommendation to comprehensively exploit the user potential preference. The model is ...

The general idea of GCL is to research the alignment between embeddings encoded from two graph contrastive representation views. In GCL-based self-supervision, ...

Feb 27, 2023 · Session-based social recommendation via dynamic graph attention networks. In WSDM. 555--563.Google Scholar Google Scholar; Hongwei Wang ...

Apr 19, 2024 · The main goal of session-based recommendation (SBR) is to analyze the list of possible next interaction items through the user's historical ...

Oct 24, 2022 · We conduct extensive experiments on three real-world recommendation datasets, and the results verify that (i) HICG achieves the state-of-the-art ...

Finally, we use contrastive learning techniques to enhance the robustness of two session embeddings. To this end, our model considers two levels of ...

Session-based recommendation (SBR) aims at predicting the next item based on an ongoing recorded session of user's behaviors. Most of existing approaches ...

This repository collects the latest research progress of Contrastive Learning (CL) and Data Augmentation (DA) in Recommender Systems.