Common wisdom in the graph neural network (GNN) community dictates that anisotropic models -- in which messages sent between nodes are a function of both the source and target node -- are required to achieve state-of-the-art performance. Benchmarks to date have demonstrated that these models perform better than comparable isotropic models -- where messages are a function of the source node only. In this work we provide empirical evidence challenging this narrative: we propose an isotropic GNN, which we call Efficient Graph Convolution (EGC), that consistently outperforms comparable anisotropic models, including the popular GAT or PNA architectures by using spatially-varying adaptive filters. In addition to raising important questions for the GNN community, our work has significant real-world implications for efficiency. EGC achieves higher model accuracy, with lower memory consumption and latency, along with characteristics suited to accelerator implementation, while being a drop-in replacement for existing architectures. As an isotropic model, it requires memory proportional to the number of vertices in the graph ($\mathcal{O}(V)$); in contrast, anisotropic models require memory proportional to the number of edges ($\mathcal{O}(E)$). We demonstrate that EGC outperforms existing approaches across 6 large and diverse benchmark datasets, and conclude by discussing questions that our work raise for the community going forward. Code and pretrained models for our experiments are provided at https://github.com/shyam196/egc.
SAHG: Sector-Anisotropic Hyperbolic Graph Model for Social Bot Detection
University of Leeds(利兹大学);University of Science and Technology of China(中国科学技术大学);South China Normal University(华南师范大学);Tsinghua University(清华大学);The Chinese University of Hong Kong(香港中文大学);Harbin University of Commerce(哈尔滨商业大学);Beijing University of Posts and Telecommunications(北京邮电大学);Peking University(北京大学);University of California, Berkeley(加州大学伯克利分校)
Shearlet Neural Operators for Anisotropic-Shock-Dominated and Multi-scale parametric partial differential equations
Coordination of Mathematical and Computational Methods National Laboratory of Scientific Computing(数学与计算方法协调国家科学计算实验室);Systems and Computational Engineering Program, COPPE/UFRJ, Federal University of Rio de Janeiro(系统与计算工程系,COPPE/UFRJ,里约热内卢联邦大学)
On Feature Selection Using Anisotropic General Regression Neural Network
University of Lausanne - Faculty of Geosciences and Environment(洛桑大学地球科学与环境学院);Scientific Computing and Research Support Unit Computer Center UNIL(洛桑大学计算机中心科学计算与研究支持单元)
A categorical embedding discontinuity-capturing shallow neural network for anisotropic elliptic interface problems
Department of Mathematics, National Central University(数学系,国立中央大学);Department of Applied Mathematics, National Yang Ming Chiao Tung University(应用数学系,国立阳明交通大学);Department of Applied Mathematics, National University of Kaohsiung(应用数学系,国立高雄大学)
Temperature-Aware Recurrent Neural Operator for Temperature-Dependent Anisotropic Plasticity in HCP Materials
organization= Mechanics \& Materials Laboratory, Department of Mechanical;Process Engineering, ETH Zürich , city= Zürich , postcode= 8092 , country= Switzerland;organization= Department of Engineering, University of Cambridge , addressline= Trumpington Street , city= Cambridge , postcode= CB2 1PZ , country= UK