Graph neural networks (GNNs) enable the analysis of graphs using deep learning, with promising results in capturing structured information in graphs. This paper focuses on creating a small graph to represent the original graph, so that GNNs trained on the size-reduced graph can make accurate predictions. We view the original graph as a distribution of receptive fields and aim to synthesize a small graph whose receptive fields share a similar distribution. Thus, we propose Graph Condesation via Receptive Field Distribution Matching (GCDM), which is accomplished by optimizing the synthetic graph through the use of a distribution matching loss quantified by maximum mean discrepancy (MMD). Additionally, we demonstrate that the synthetic graph generated by GCDM is highly generalizable to a variety of models in evaluation phase and that the condensing speed is significantly improved using this framework.
Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching
National University of Singapore(新加坡国立大学);A*STAR Centre for Frontier AI Research (CFAR)(新加坡科技研究局前沿人工智能研究中心);Shanghai AI Laboratory(上海人工智能实验室);University of Nevada, Reno(内华达大学雷诺分校)
Discourse-level Relation Extraction via Graph Pooling
Information Sciences Institute, University of Southern California(南加州大学信息科学研究所);Michigan State University(密歇根州立大学);University of California, Los Angeles(加州大学洛杉矶分校)
Institute of Information Science, Beijing Jiaotong University(信息科学学院,北京交通大学);Visual Intelligence + X International Joint Laboratory of the Ministry of Education(教育部视觉智能+X国际联合实验室);Medical Big Data Research Center, Chinese PLA General Hospital Beijing, China(中国人民解放军总医院医学大数据研究中心)
Nonparametric Distribution Matching for Self-Supervised Whole-Slide Image Condensation
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Washington State University(华盛顿州立大学);Hanoi Medical University(河内医科大学);VinUniversity(文森大学);Hanoi University of Science and Technology(河内科技大学)
Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation
University of Oxford(牛津大学);Shanghai Jiao Tong University(上海交通大学);University of Nottingham(诺丁汉大学);Chinese Academy of Sciences(中国科学院);University of Edinburgh(爱丁堡大学)
M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);University of Chinese Academy of Sciences(中国科学院大学);Shanghai University(上海大学)
Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence
Yardi School of Artificial Intelligence, IIT Delhi, India(印度德里理工学院Yardi人工智能学院);Department of Computer Science and Engineering, IIT Delhi, India(印度德里理工学院计算机科学与工程系);Department of Chemical Engineering, IIT Delhi, India(印度德里理工学院化学工程系);Indian Institute of Technology Delhi, Abu Dhabi, Zayed City, Abu Dhabi, UAE(印度德里理工学院阿布扎赫德分校,扎耶德城,阿布扎赫德,阿联酋)