A5074529703- Recommender Systems and Techniques
- Advanced Graph Neural Networks
- Topic Modeling
- Material Properties and Failure Mechanisms
- BIM and Construction Integration
- High-Velocity Impact and Material Behavior
- Fatigue and fracture mechanics
Baidu (China)
2024
PLA Army Engineering University
2024
University of Hong Kong
2024
National Cheng Kung University
1993
The problem of data sparsity has long been a challenge in recommendation systems, and previous studies have attempted to address this issue by incorporating side information. However, approach often introduces effects such as noise, availability issues, low quality, which turn hinder the accurate modeling user preferences adversely impact performance. In light recent advancements large language models (LLMs), possess extensive knowledge bases strong reasoning capabilities, we propose novel...
Recommender systems have seen significant advancements with the influence of deep learning and graph neural networks, particularly in capturing complex user-item relationships.However, these graph-based recommenders heavily depend on ID-based data, potentially disregarding valuable textual information associated users items, resulting less informative learned representations.Moreover, utilization implicit feedback data introduces potential noise bias, posing challenges for effectiveness user...