Welcome to the DSAI Lab at the HKUST(GZ), our research focuses on a variety of topics within the realm of artificial intelligence, including but not limited to
- Graph Foundation Model
- Data Mining
- AI for Science
- Large Language Model
GraphWiz: An Instruction-Following Language Model for Graph Problems [github]
ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs [github]
All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretraining [github]
Relaxing Continuous Constraints of Equivariant Graph Neural Networks for Physical Dynamics Learning [github]
Parameter Efficient Fine-Tuning with Discrete Fourier Transform [github]
A Survey of Graph Meets Large Language Model: Progress and Future Directions [github]
Weakly Supervised Anomaly Detection via Knowledge-Data Alignment [github]
Protein Multimer Structure Prediction via Prompt Learning [github]
Deep Reinforcement Learning for Modelling Protein Complexes
SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases
GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection [github]
Deep Insights into Noisy Pseudo Labeling on Graph Data [github]
Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters [github]
Orca: A Few-shot Benchmark for Chinese Conversational Machine Reading Comprehension [github]
Nature Response Generation for Chinese Reading Comprehension [github]
A Co-training Approach for Noisy Time Series Learning [github]
Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Series [github]
Alleviating Over-smoothing for Unsupervised Sentence Representation [github]
Structural Contrastive Pretraining for Cross-Lingual Comprehension [github]
A Fused Gromov-Wasserstein Framework for Unsupervised Knowledge Graph Entity Alignment [github]
Hierarchical Graph Learning for Protein-Protein Interaction [github]
Handling Missing Data via Max-Entropy Regularized Graph Autoencoder Human Mobility Modeling During the COVID-19 Pandemic via Deep Graph Diffusion Infomax Wiener Graph Deconvolutional Network Improves Graph Self-Supervised Learning
Robust Attributed Graph Alignment via Joint Structure Learning and Optimal Transport [github]
Rethinking Graph Neural Networks for Anomaly Detection [github]