Graph representation learning has recently been applied to a broad spectrum of problems ranging from computer graphics and chemistry to high energy physics and social media. The popularity of graph neural networks has sparked interest, both in academia and in industry, in developing methods that scale to very large graphs such as Facebook or Twitter social networks. In most of these approaches, the computational cost is alleviated by a sampling strategy retaining a subset of node neighbors or subgraphs at training time. In this paper we propose a new, efficient and scalable graph deep learning architecture which sidesteps the need for graph sampling by using graph convolutional filters of different size that are amenable to efficient precomputation, allowing extremely fast training and inference. Our architecture allows using different local graph operators (e.g. motif-induced adjacency matrices or Personalized Page Rank diffusion matrix) to best suit the task at hand. We conduct extensive experimental evaluation on various open benchmarks and show that our approach is competitive with other state-of-the-art architectures, while requiring a fraction of the training and inference time. Moreover, we obtain state-of-the-art results on ogbn-papers100M, the largest public graph dataset, with over 110 million nodes and 1.5 billion edges.
Accelerating Scalable Graph Neural Network Inference with Node-Adaptive Propagation
The University of Queensland（昆士兰大学）；Peking University（北京大学）；National Engineering Laboratory for Big Data Analysis and Applications（国家大数据分析与应用工程实验室）；Beijing University of Posts and Telecommunications（北京邮电大学）；Griffith University（格里菲斯大学）
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）
Dual Learning-based Video Coding with Inception Dense Blocks
Fudan University（复旦大学）；Waseda University（早稻田大学）
本文针对PCS Grand Challenge提出了一种基于双重学习的帧内编码方法。该方法主要由帧内预测和重构滤波两部分组成。它们使用不同的网络结构，基于神经网络的帧内预测使用全连接网络来预测块，而基于神经网络的重构滤波使用卷积网络。与以往的滤波工作不同的是，我们在重构滤波网络中使用了具有更强大特征提取能力的网络。并且滤波单元为块级，从而实现更精确的滤波补偿。据我们所知，在所有基于学习的方法中，这是第一次尝试在一个应用中结合两个不同的网络，并且我们在HEVC测试序列上实现了AI配置的最新性能。实验结果表明，与HM-16.20基线相比，我们的方法对于提供的8个序列导致显著的BD速率节省（对于所有帧内和随机访问编码，分别平均降低10.24%和3.57%的比特率）。对于HEVC测试序列，与HM-16.20基线相比，我们的模型还实现了9.70%的BD速率节省。
An Inception-Residual-Based Architecture with Multi-Objective Loss for Detecting Respiratory Anomalies
Queen Mary University of London（伦敦玛丽女王大学）；University of Essex（埃塞克斯大学）；Austrian Institute of Technology（奥地利技术研究所）；Amazon Alexa（亚马逊Alexa）；University of Oxford（牛津大学）
