M
Meng Liu
Researcher at Texas A&M University
Publications - 21
Citations - 599
Meng Liu is an academic researcher from Texas A&M University. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 7, co-authored 11 publications receiving 178 citations.
Papers
More filters
Proceedings ArticleDOI
Towards Deeper Graph Neural Networks
TL;DR: This work provides a systematical analysis and theoretical analysis of the over-smoothing issue and proposes Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields to learn graph node representations from larger receptive fields.
Proceedings ArticleDOI
Towards Deeper Graph Neural Networks
TL;DR: Deep Adaptive Graph Neural Network (DAGNN) as mentioned in this paper proposes to adaptively incorporate information from large receptive fields by decoupling representation transformation and propagation in current graph convolution operations.
Journal Article
Non-Local Graph Neural Networks
TL;DR: This work proposes a simple yet effective non-local aggregation framework with an efficient attention-guided sorting for GNNs that significantly outperform previous state-of-the-art methods on seven benchmark datasets of disassortative graphs, in terms of both model performance and efficiency.
Proceedings ArticleDOI
Generating 3D Molecules for Target Protein Binding
TL;DR: This work proposes a novel and effective framework, known as GraphBP, to generate 3D molecules that bind to given proteins by placing atoms of specific types and locations to the given binding site one by one.
Posted Content
Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discovery
TL;DR: In this article, the authors developed a suite of comprehensive machine learning methods and tools spanning different computational models, molecular representations, and loss functions for molecular property prediction and drug discovery and achieved the #1 ranking in terms of both ROC AUC and PRC-AUC on the AI Cures Open Challenge related to COVID-19.