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
Graph2Vid: Flow graph to Video Grounding for Weakly-supervised Multi-Step Localization
Nikita Dvornik, Isma Hadji, Hai Pham, Dhaivat Bhatt, Brais Martinez, Afsaneh Fazly, Allan D. Jepson
Region2Vec: Community Detection on Spatial Networks Using Graph Embedding with Node Attributes and Spatial Interactions
Yunlei Liang, Jiawei Zhu, Wen Ye, Song Gao
Spectral Augmentation for Self-Supervised Learning on Graphs
Lu Lin, Jinghui Chen, Hongning Wang
Inability of a graph neural network heuristic to outperform greedy algorithms in solving combinatorial optimization problems like Max-Cut
Stefan Boettcher
Gradient Gating for Deep Multi-Rate Learning on Graphs
T. Konstantin Rusch, Benjamin P. Chamberlain, Michael W. Mahoney, Michael M. Bronstein, Siddhartha Mishra