What is the simplest, but still effective, graph neural network (GNN) that we can design, say, for node classification? Einstein said that we should "make everything as simple as possible, but not simpler." We rephrase it into the 'careful simplicity' principle: a carefully-designed simple model can outperform sophisticated ones in real-world tasks, where data are scarce, noisy, and spuriously correlated. Based on that principle, we propose SlenderGNN that exhibits four desirable properties: It is (a) accurate, winning or tying on 11 out of 13 real-world datasets; (b) robust, being the only one that handles all settings (heterophily, random structure, useless features, etc.); (c) fast and scalable, with up to 18 times faster training in million-scale graphs; and (d) interpretable, thanks to the linearity and sparsity we impose. We explain the success of SlenderGNN via a systematic study on existing models, comprehensive sanity checks, and ablation studies on its design decisions.

翻译：最简单、但依然有效的图形神经网络(GNN)是什么,我们可以设计,比如,节点分类?爱因斯坦说,我们应该“尽可能简单,但不能简单。” 我们把它改写成“小心简单”原则:精心设计的简单模型可以超越现实世界任务中的复杂模型,因为数据稀缺、吵闹和虚假相关。基于这一原则,我们建议SlenderGNNN能够展示四种可取的属性:(a) 精确、赢取或绑紧13个真实世界数据集中的11个;(b) 强大,是唯一能够处理所有设置(偏差、随机结构、无用特征等);(c) 快速和可缩放,在百万尺度的图表中培训速度可达18倍;(d) 由于我们强加的线性与紧张性,可以解释。我们通过对现有模型的系统研究、全面理智检查以及设计决定的折叠研究,我们解释了SlenderGNNN的成功之处。