Graph Drawing
Graph drawing research focuses on efficiently representing and manipulating graph-structured data, aiming to optimize algorithms for tasks like pathfinding, substructure counting, and graph classification. Current research emphasizes developing novel algorithms, including those based on reinforcement learning, linear programming, and graph neural networks (GNNs), to improve computational efficiency and address challenges like heterophily and scalability in large graphs. These advancements have significant implications for diverse fields, enabling faster and more accurate analysis of complex networks in areas such as social sciences, robotics, and materials science.
Papers
Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules
Jong Youl Choi, Pei Zhang, Kshitij Mehta, Andrew Blanchard, Massimiliano Lupo Pasini
A flexible PageRank-based graph embedding framework closely related to spectral eigenvector embeddings
Disha Shur, Yufan Huang, David F. Gleich
Graph Spatio-Spectral Total Variation Model for Hyperspectral Image Denoising
Shingo Takemoto, Kazuki Naganuma, Shunsuke Ono
Understanding convolution on graphs via energies
Francesco Di Giovanni, James Rowbottom, Benjamin P. Chamberlain, Thomas Markovich, Michael M. Bronstein
Efficient and effective training of language and graph neural network models
Vassilis N. Ioannidis, Xiang Song, Da Zheng, Houyu Zhang, Jun Ma, Yi Xu, Belinda Zeng, Trishul Chilimbi, George Karypis