A5073466350- DNA and Biological Computing
- Neural Networks and Applications
- Food composition and properties
- Data Mining Algorithms and Applications
- Neural Networks and Reservoir Computing
- Ruminant Nutrition and Digestive Physiology
- Microbial Metabolic Engineering and Bioproduction
- Phytoestrogen effects and research
- Growth Hormone and Insulin-like Growth Factors
- Model-Driven Software Engineering Techniques
- Product Development and Customization
- Topic Modeling
- Biofuel production and bioconversion
- Advanced Memory and Neural Computing
- Semantic Web and Ontologies
- Cellular Automata and Applications
- Multimodal Machine Learning Applications
- Advanced Graph Neural Networks
- Manufacturing Process and Optimization
- Distributed and Parallel Computing Systems
- Natural Language Processing Techniques
Michigan State University
1997-2025
Jiangxi Agricultural University
2017
Graphs play an important role in representing complex relationships various domains like social networks, knowledge graphs, and molecular discovery. With the advent of deep learning, Graph Neural Networks (GNNs) have emerged as a cornerstone Machine Learning (Graph ML), facilitating representation processing graphs. Recently, LLMs demonstrated unprecedented capabilities language tasks are widely adopted variety applications such computer vision recommender systems. This remarkable success...
Recent years have witnessed significant advancements in graph machine learning (GML), with its applications spanning numerous domains. However, the focus of GML has predominantly been on developing powerful models, often overlooking a crucial initial step: constructing suitable graphs from common data formats, such as tabular data. This construction process is fundamental to applying graphbased yet it remains largely understudied and lacks formalization. Our research aims address this gap by...
A fundamental challenge in understanding graph neural networks (GNNs) lies characterizing their optimization dynamics and loss landscape geometry, critical for improving interpretability robustness. While mode connectivity, a lens analyzing geometric properties of landscapes has proven insightful other deep learning architectures, its implications GNNs remain unexplored. This work presents the first investigation connectivity GNNs. We uncover that exhibit distinct non-linear diverging from...
Foundation models such as GPT-4 for natural language processing (NLP), Flamingo computer vision (CV), have set new benchmarks in AI by delivering state-of-the-art results across various tasks with minimal task-specific data. Despite their success, the application of these to graph domain is challenging due relational nature graph-structured To address this gap, we propose Graph Model (GFM) Workshop, first workshop GFMs, dedicated exploring adaptation and development foundation specifically...
Given the ubiquity of graph data and its applications in diverse domains, building a Graph Foundation Model (GFM) that can work well across different graphs tasks with unified backbone has recently garnered significant interests. A major obstacle to achieving this goal stems from fact domains often exhibit node features. Inspired by multi-modal models align modalities natural language, text been adopted provide feature space for graphs. Despite great potential these text-space GFMs, current...