Recommender systems mitigate information overload by offering personalized suggestions
to users. As the interactions between users and items can inherently be depicted as a …

Graph contrastive learning (GCL), designing contrastive objectives to learn embeddings
from augmented graphs, has become a prevailing method for extracting embeddings from …

To analyze and process graph data, researchers have proposed Graph Neural Network
(GNN) models. In this paper, we focus on methods for boosting the performance of existing …

Ensuring the relevance of text between user queries and products is vital for e-commerce
search engines to enhance user experience and facilitate finding desired products. Thanks …

Unsupervised graph representation learning, ie, learning node or graph embeddings from
graph data in an unsupervised manner, has become an important problem when we study …