A5045825946- Recommender Systems and Techniques
- Advanced Graph Neural Networks
- Colorectal and Anal Carcinomas
- Advanced Bandit Algorithms Research
- Spinal Fractures and Fixation Techniques
- Spine and Intervertebral Disc Pathology
- Data Management and Algorithms
- Bone and Joint Diseases
- Data Mining Algorithms and Applications
- Colorectal Cancer Surgical Treatments
- Evolutionary Algorithms and Applications
- Radiomics and Machine Learning in Medical Imaging
- Topic Modeling
Peking University
2024
Microsoft Research Asia (China)
2024
Central South University
2024
Fuzhou University
2024
Jinan University
2024
Hong Kong University of Science and Technology
2024
University of Hong Kong
2024
Hong Kong Polytechnic University
2024
Objective: To explore the effectiveness of percutaneous kyphoplasty (PKP) combined with different anti-osteoporosis drugs in treatment osteoporotic vertebral compression fractures (OVCF) by assessing bone mineral density, pain, lumbar functional recovery, and incidence refractures after therapy. Methods: In this single-center retrospective study, medical records 138 patients OVCF who underwent PKP Third Hospital Hebei Medical University between January 2021 October 2022 were retrospectively...
In the realm of personalized recommender systems, challenge adapting to evolving user preferences and continuous influx new users items is paramount. Conventional models, typically reliant on a static training-test approach, struggle keep pace with these dynamic demands. Streaming recommendation, particularly through continual graph learning, has emerged as novel solution. However, existing methods in this area either rely historical data replay, which increasingly impractical due stringent...
We investigate node representation learning on text-attributed graphs (TAGs), where nodes are associated with text information. Although recent studies graph neural networks (GNNs) and pretrained language models (PLMs) have exhibited their power in encoding network signals, respectively, less attention has been paid to delicately coupling these two types of TAGs. Specifically, existing GNNs rarely model each a contextualized way; PLMs can hardly be applied characterize structures due...
Session-based recommendation (SBR) systems, traditionally reliant on complex graph neural networks (GNNs), often face challenges with marginal performance improvements despite increased model complexity. In this paper, we dissect the classical GNN-based SBR models and empirically find that sophisticated GNN propagations might be redundant, given readout module plays a significant role in models. Based observation, introduce Atten-Mixer+, an advanced iteration of our previously developed...
Recent advancements in large language models (LLMs) have significantly enhanced the ability of LLM-based systems to perform complex tasks through natural processing and tool interaction. However, optimizing these for specific remains challenging, often requiring manual interventions like prompt engineering hyperparameter tuning. Existing automatic optimization methods, such as textual feedback-based techniques (e.g., TextGrad), tend focus on immediate feedback, analogous using derivatives...