244 citations · 377 across the 9 of their papers we have counts for
10 papers
Node-level Graph Neural Architecture Search Framework
Lintao Yanga, Sirui Lia, Yaqing Wang +4
In recent years, Graph Neural Networks (GNNs) and architecture search frameworks have gained extensive application in non-Euclidean data processing, attributable to their superior…
Enhancing Node Representations for Real-World Complex Networks with Topological Augmentation
Xiangyu Zhao, Zehui Li, Mingzhu Shen +3
Graph augmentation methods play a crucial role in improving the performance and enhancing generalisation capabilities in Graph Neural Networks (GNNs). Existing graph augmentation m…
Will More Expressive Graph Neural Networks do Better on Generative Tasks?
Xiandong Zou, Xiangyu Zhao, Pietro Liò +1
Graph generation poses a significant challenge as it involves predicting a complete graph with multiple nodes and edges based on simply a given label. This task also carries fundam…
Hybrid Graph: A Unified Graph Representation with Datasets and Benchmarks for Complex Graphs
Zehui Li, Xiangyu Zhao, Mingzhu Shen +3
Graphs are widely used to encapsulate a variety of data formats, but real-world networks often involve complex node relations beyond only being pairwise. While hypergraphs and hier…
Task-Agnostic Graph Neural Network Evaluation via Adversarial Collaboration
Xiangyu Zhao, Hannes Stärk, Dominique Beaini +2
It has been increasingly demanding to develop reliable methods to evaluate the progress of Graph Neural Network (GNN) research for molecular representation learning. Existing GNN b…
3D Infomax improves GNNs for Molecular Property Prediction
Hannes Stärk, Dominique Beaini, Gabriele Corso +4
Molecular property prediction is one of the fastest-growing applications of deep learning with critical real-world impacts. Including 3D molecular structure as input to learned mod…
Directional Graph Networks
Dominique Beaini, Saro Passaro, Vincent Létourneau +3
The lack of anisotropic kernels in graph neural networks (GNNs) strongly limits their expressiveness, contributing to well-known issues such as over-smoothing. To overcome this lim…
Learned Low Precision Graph Neural Networks
Yiren Zhao, Duo Wang, Daniel Bates +3
Deep Graph Neural Networks (GNNs) show promising performance on a range of graph tasks, yet at present are costly to run and lack many of the optimisations applied to DNNs. We show…
Principal Neighbourhood Aggregation for Graph Nets
Gabriele Corso, Luca Cavalleri, Dominique Beaini +2
Graph Neural Networks (GNNs) have been shown to be effective models for different predictive tasks on graph-structured data. Recent work on their expressive power has focused on is…
Probabilistic Dual Network Architecture Search on Graphs
Yiren Zhao, Duo Wang, Xitong Gao +3
We present the first differentiable Network Architecture Search (NAS) for Graph Neural Networks (GNNs). GNNs show promising performance on a wide range of tasks, but require a larg…