1 code implementation • Proceedings of the AAAI Conference on Artificial Intelligence 2023 • Zeng, D., Liu, Chen, W., Zhou, L., Zhang, M., & Qu, H
Despite the great achievements of Graph Neural Networks (GNNs) in graph learning, conventional GNNs struggle to break through the upper limit of the expressiveness of first-order Weisfeiler-Leman graph isomorphism test algorithm (1-WL) due to the consistency of the propagation paradigm of GNNs with the 1-WL. Based on the fact that it is easier to distinguish the original graph through subgraphs, we propose a novel framework neural network framework called Substructure Aware Graph Neural Networks (SAGNN) to address these issues.
Ranked #7 on Graph Regression on ZINC-500k
no code implementations • 11 Jan 2021 • Limon Barua, Bo Zou, Yan, Zhou, Yulin Liu
Extensive post-modeling investigation is conducted in a comparative manner between 2009 and 2017, including quantifying the importance of each input variable in predicting online shopping demand, and characterizing value-dependent relationships between demand and the input variables.
no code implementations • 5 Sep 2020 • Hongwei, Zhou, Oskar Elek, Pranav Anand, Angus G. Forbes
Word embeddings are a popular way to improve downstream performances in contemporary language modeling.
1 code implementation • IEEE Transactions on Image Processing 2020 • Zhou, Tianfei; Li, Jianwu; Wang, Shunzhou; Tao, Ran; Shen, Jianbing
To further demonstrate the generalization ability of our spatiotemporal learning framework, we extend MATNet to another relevant task: dynamic visual attention prediction (DVAP).
Ranked #4 on Video Polyp Segmentation on SUN-SEG-Hard (Unseen)