A5114514278- Advanced Sensor and Control Systems
- Advanced Decision-Making Techniques
- Robotic Path Planning Algorithms
- Advanced Graph Neural Networks
- Natural Language Processing Techniques
- Complex Network Analysis Techniques
- AI-based Problem Solving and Planning
- Evaluation Methods in Various Fields
- Semiconductor materials and devices
- Advanced Clustering Algorithms Research
- Machine Learning and Algorithms
State Grid Corporation of China (China)
2025
University of Electronic Science and Technology of China
2024
The rapid growth of model scale has necessitated substantial computational resources for fine-tuning. Existing approach such as Low-Rank Adaptation (LoRA) sought to address the problem handling large updated parameters in full However, LoRA utilize random initialization and optimization low-rank matrices approximate weights, which can result suboptimal convergence an accuracy gap compared To these issues, we propose LoLDU, a Parameter-Efficient Fine-Tuning (PEFT) that significantly reduces...
Heterophily, or the tendency of connected nodes in networks to have different class labels dissimilar features, has been identified as challenging for many Graph Neural Network (GNN) models. While challenges applying GNNs node classification when display strong heterophily are well understood, it is unclear how affects GNN performance other important graph learning tasks where not available. In this work, we focus on link prediction task and systematically analyze impact features...
Large language models (LLMs) have become increasingly pivotal across various domains, especially in handling complex data types. This includes structured processing, as exemplified by ChartQA and ChatGPT-Ada, multimodal unstructured processing seen Visual Question Answering (VQA). These areas attracted significant attention from both industry academia. Despite this, there remains a lack of unified evaluation methodologies for these diverse scenarios. In response, we introduce BabelBench, an...