Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating, and …
Invariant graph representation learning aims to learn the invariance among data from different environments for out-of-distribution generalization on graphs. As the graph …
Graph-structured data exhibits universality and widespread applicability across diverse domains, such as social network analysis, biochemistry, financial fraud detection, and …
X Li, S Gui, Y Luo, S Ji - arXiv preprint arXiv:2306.08076, 2023 - arxiv.org
Out-of-distribution (OOD) generalization deals with the prevalent learning scenario where test distribution shifts from training distribution. With rising application demands and inherent …
Z Li, Z Xu, R Cai, Z Yang, Y Yan, Z Hao, G Chen… - arXiv preprint arXiv …, 2023 - arxiv.org
Although graph neural networks have achieved great success in the task of molecular property prediction in recent years, their generalization ability under out-of-distribution …
Y Huang, L Sun, H Wang, S Wu… - International …, 2024 - proceedings.mlr.press
Large language models (LLMs) have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many …
H Wu, F Xu, Y Duan, Z Niu, W Wang, G Lu… - arXiv preprint arXiv …, 2024 - arxiv.org
This paper proposes a two-stage framework named ST-PAD for spatio-temporal fluid dynamics modeling in the field of earth sciences, aiming to achieve high-precision …
S Gui, H Yuan, J Wang, Q Lao, K Li… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
We investigate the explainability of graph neural networks (GNNs) as a step toward elucidating their working mechanisms. While most current methods focus on explaining …
S Liu, D Zou, H Zhao, P Li - arXiv preprint arXiv:2403.01092, 2024 - arxiv.org
Graph-based methods, pivotal for label inference over interconnected objects in many real- world applications, often encounter generalization challenges, if the graph used for model …