How can we find the right graph for semi-supervised learning? In real world applications, the choice of which edges to use for computation is the first step in any graph learning process. Interestingly, there are often many types of similarity available to choose as the edges between nodes, and the choice of edges can drastically affect the performance of downstream semi-supervised learning systems. However, despite the importance of graph design, most of the literature assumes that the graph is static. In this work, we present Grale, a scalable method we have developed to address the problem of graph design for graphs with billions of nodes. Grale operates by fusing together different measures of(potentially weak) similarity to create a graph which exhibits high task-specific homophily between its nodes. Grale is designed for running on large datasets. We have deployed Grale in more than 20 different industrial settings at Google, including datasets which have tens of billions of nodes, and hundreds of trillions of potential edges to score. By employing locality sensitive hashing techniques,we greatly reduce the number of pairs that need to be scored, allowing us to learn a task specific model and build the associated nearest neighbor graph for such datasets in hours, rather than the days or even weeks that might be required otherwise. We illustrate this through a case study where we examine the application of Grale to an abuse classification problem on YouTube with hundreds of million of items. In this application, we find that Grale detects a large number of malicious actors on top of hard-coded rules and content classifiers, increasing the total recall by 89% over those approaches alone.
LTCI & CMAP , Télécom Paris & Ecole Polytechnique, IP Paris（巴黎电信学院与应用数学研究所、巴黎电信学院与巴黎高等理工学院、IP巴黎）；LTCI, Télécom Paris, IP Paris（巴黎电信学院、巴黎电信学院、IP巴黎）；CMAP, Ecole Polytechnique, IP Paris（应用数学研究所、巴黎高等理工学院、IP巴黎）
Inverse designing metamaterials with programmable nonlinear functional responses in graph space
University of California Berkeley（加州大学伯克利分校）；University of California Los Angeles（加州大学洛杉矶分校）；Penn State University（宾州州立大学）；CNRS（法国国家科学研究中心）；Institut Jean Lamour（让·拉穆尔研究所）
Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Paradigm. Inc.（第四范式有限公司）；Lenovo（联想）
Enhancing Intra-class Information Extraction for Heterophilous Graphs: One Neural Architecture Search Approach
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Paradigm. Inc.（第四范式公司）；Lenovo（联想集团）；Tsinghua University（清华大学）
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Agricultural Information Institute, China Academy of Agricultural Sciences（中国农业科学院农业信息研究所）；School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；Peng Cheng Laboratory（鹏城实验室）
GrassNet: State Space Model Meets Graph Neural Network
School of Computer Science and Technology（计算机科学与技术学院）；Beijing Jiaotong University（北京交通大学）；Department of Computer Science（计算机科学系）；Stony Brook University（石溪大学）
Designing ReLU Generative Networks to Enumerate Trees with a Given Tree Edit Distance
Bioinformatics Center, Institute for Chemical Research, Department of Intelligence Sciences and Technology, Kyoto University（生物信息学中心、化学研究所、智能科学与技术系、京都大学）
AntibodyFlow: Normalizing Flow Model for Designing Antibody Complementarity-Determining Regions
School of Electrical Engineering and Computer Science, Nanjing University of Aeronautics and Astronautics（南京航空航天大学电子工程与计算机科学学院）；School of Computer Science and Technology, North University of China（中北大学计算机科学与技术学院）；School of Semiconductor and Physics, North University of China（中北大学半导体与物理学院）
