Sampling is a critical operation in Graph Neural Network (GNN) training that helps reduce the cost. Previous literature has explored improving sampling algorithms via mathematical and statistical methods. However, there is a gap between sampling algorithms and hardware. Without consideration of hardware, algorithm designers merely optimize sampling at the algorithm level, missing the great potential of promoting the efficiency of existing sampling algorithms by leveraging hardware features. In this paper, we pioneer to propose a unified programming model for mainstream sampling algorithms, termed GNNSampler, covering the critical processes of sampling algorithms in various categories. Second, to leverage the hardware feature, we choose the data locality as a case study, and explore the data locality among nodes and their neighbors in a graph to alleviate irregular memory access in sampling. Third, we implement locality-aware optimizations in GNNSampler for various sampling algorithms to optimize the general sampling process. Finally, we emphatically conduct experiments on large graph datasets to analyze the relevance among training time, accuracy, and hardware-level metrics. Extensive experiments show that our method is universal to mainstream sampling algorithms and helps significantly reduce the training time, especially in large-scale graphs.
DiskGNN: Bridging I/O Efficiency and Model Accuracy for Out-of-Core GNN Training
Southern University of Science and Technology（南方科技大学）；UC Berkeley（加州大学伯克利分校）；Centre for Perceptual and Interactive Intelligence（感知与交互智能中心）；New York University（纽约大学）；Amazon（亚马逊）；AWS Shanghai AI Lab（亚马逊云科技上海人工智能实验室）
Towards Bridging Generalization and Expressivity of Graph Neural Networks
School of Computing, Australian National University（澳大利亚国立大学计算机学院）；Data61, CSIRO（联邦科学与工业研究组织Data61研究院）；Department of Computer Science, University of Antwerp（安特卫普大学计算机学院）；CSE & GSAI, POSTECH（浦项科技大学计算机科学与工程系及人工智能研究生院）
Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks
Mississippi State University（密西西比州立大学）；Virginia Tech（弗吉尼亚理工大学）；South Dakota State University（南达科他州立大学）；Emory University（埃默里大学）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）；JD.COM Silicon Valley Research Center（京东硅谷研究中心）；IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）
Bridging the Gap of AutoGraph between Academia and Industry: Analysing AutoGraph Challenge at KDD Cup 2020
Paradigm（第四范式）；Stanford University（斯坦福大学）；Tsinghua University（清华大学）；ChaLearn；LISN/INRIA/CNRS, University Paris-Saclay（巴黎萨克雷大学LISN/法国国家信息与自动化研究所/法国国家科学研究中心）
图结构化数据在日常生活和科学领域中无处不在，越来越受到人们的关注。图神经网络（GNN）已被证明是有效的建模图结构的数据和许多变体的GNN架构已被提出。然而，根据不同的数据集调整架构通常需要大量的人力。研究人员自然会在图学习上采用自动化机器学习，旨在减少人力投入并实现性能最佳的GNN，但他们的方法更侧重于架构搜索。为了了解GNN从业者的自动化解决方案，我们在KDD Cup 2020上组织了AutoGraph Challenge，重点关注用于节点分类的自动化图神经网络。我们收到了来自美团、阿里巴巴和Twitter等工业科技公司的顶级解决方案，这些解决方案已经在Github上开源。在与学术界的解决方案进行详细比较后，我们量化了学术界和工业界在建模范围，有效性和效率方面的差距，并表明（1）学术界AutoML for Graph解决方案专注于GNN架构搜索，而工业解决方案，特别是KDD杯的获奖者，倾向于获得整体解决方案（2）仅通过神经架构搜索，学术界解决方案的平均精度达到工业解决方案的97.3%（3）学术界解决方案的成本很低，只需几个GPU小时，而工业解决方案需要几个月的劳动力。学术解决方案包含的参数也少得多。
OmniPMNet: Bridging discrete and gridded PM10 forecasts via omni-query neural processes
ColorfulClouds Technology Co., Ltd.（彩云科技有限公司）；School of Systems Science, Beijing Normal University（北京师范大学系统科学学院）；D-ITET, ETH Zurich（苏黎世联邦理工学院动态信息与电气工程系）
Bridging Graph Structure and Knowledge-Guided Editing for Interpretable Temporal Knowledge Graph Reasoning
Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University（数据科学与人工智能系，香港理工大学）；School of Cybersecurity, Northwestern Polytechnical University（网络安全学院，西北工业大学）；Department of Electronic Engineering, Tsinghua University（电子工程系，清华大学）；School of Mechanical Engineering, Northwestern Polytechnical University（机械工程学院，西北工业大学）；School of Mathematics and Statistics, Xi’an Jiaotong University（数学与统计学院，西安交通大学）
EXGC: Bridging Efficiency and Explainability in Graph Condensation
University of Science and Technology of China（中国科学技术大学）；Hunan University（湖南大学）；Tongji University（同济大学）；National University of Singapore（新加坡国立大学）；Institute of Dataspace（数据空间研究院）
If You Want to Be Robust, Be Wary of Initialization
KTH Stockholm, Sweden（瑞典斯德哥尔摩皇家理工学院）；LIX, Ecole Polytechnique IP Paris, France（法国巴黎高等理工学院LIX研究所）；KTH & Ecole Polytechnique Stockholm, Sweden（瑞典斯德哥尔摩皇家理工学院及巴黎高等理工学院）；UM6P Benguerir, Morocco（摩洛哥本格里大学）
Bridging Cognitive Neuroscience and Graph Intelligence: Hippocampus-Inspired Multi-View Hypergraph Learning for Web Finance Fraud
School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）；School of Computer Science and Technology, Donghua University（东华大学计算机科学与技术学院）
Inductive Graph Alignment Prompt: Bridging the Gap between Graph Pre-training and Inductive Fine-tuning From Spectral Perspective
Peking University（北京大学）；Hong Kong University of Science and Technology（香港科技大学）；Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心）
Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection
Department of Computer Science, Virginia Tech, Virginia, USA（弗吉尼亚理工大学计算机科学系）；Department of Computer Science, Manitoba, Canada（曼尼托巴大学计算机科学系）；Department of Computer Science, University of Toledo, Ohio, USA（托莱多大学计算机科学系）；AI Initiative, University of Central Florida, Florida, USA（佛罗里达大学人工智能倡议）
Bridging the Gap between Sparse Matrix Reordering and Factorization: A Deep Learning Framework for Fill-in Reduction
Institute of Software, Chinese Academy of Sciences, Beijing, China（中国科学院软件研究所，北京，中国）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国）
Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack
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）；Renmin University of China（中国人民大学）；Zhongguancun Laboratory（中关村实验室）；Griffith University（格里菲斯大学）
Inference of Sequential Patterns for Neural Message Passing in Temporal Graphs
University of Zurich（苏黎世大学）；Julius-Maximilians-Universität Würzburg（维尔茨堡大学）；Center for Artificial Intelligence and Data Science (CAIDAS)（人工智能与数据科学中心）；Chair of Machine Learning for Complex Networks（复杂网络机器学习主席席位）
A New Workflow for Materials Discovery Bridging the Gap Between Experimental Databases and Graph Neural Networks
Department of Physics, University at Buffalo, State University of New York, Buffalo, NY；Department of Computer Science \& Engineering, University at Buffalo, State University of New York, Buffalo, NY；Institute for Artificial Intelligence；Data Science, University at Buffalo, State University of New York, Buffalo, NY
