Events Search and Views Navigation

Event Views Navigation

Today

Sentimentally enhanced conversation recommender system

A conversation recommender system (CRS) aims to provide high-quality recommendations to users in fewer conversation turns. Existing studies often rely on knowledge graphs and entities mentioned in dialogues to enhance the representation of entity information. However, they fail to thoroughly explore users’ emotional tendencies toward entities or effectively differentiate the varying impacts of different entities on user preferences. Recently, Liu et.al. proposed an innovative Sentimentally Enhanced Conversation Recommender system (SECR). In this presentation, the SECR method will be explained and described how this method captured users' emotional inclinations toward entities.

Explainable Spatio-Temporal GNNs

Spatio-temporal graph neural networks (STGNNs) have gained popularity as a powerful tool for effectively modeling spatio-temporal dependencies in diverse real-world urban applications, including intelligent transportation and public safety. However, the blackbox nature of STGNNs limits their interpretability, hindering their application in scenarios related to urban resource allocation and policy formulation. To bridge this gap, they propose an Explainable Spatio-Temporal Graph Neural Networks (STExplainer) framework that enhances STGNNs with inherent explainability, enabling them to provide accurate predictions and faithful explanations simultaneously.