为了结合GNN和MLP的优点来搭建一个高准确率且低延迟的模型,这篇文章提出了一个模型叫做Graph-less Neural Network (GLNN)。具体来说,GLNN是一种涉及从教师GNN到学生MLP的知识蒸馏(knowledge distillation)模型。经过训练后的学生MLP即为最终的GLNN,所以GLNN在训练中享有图拓扑结构(graph topology)的好处,但在推理中...
Method 为了结合 GNN 和 MLP 的优点来搭建一个高准确率且低延迟的模型,这篇文章提出了一个模型叫做 Graph-less Neural Network(GLNN)。具体来说,GLNN 是一种涉及从教师 GNN 到学生 MLP 的知识蒸馏(knowledge distillation)模型。经过训练后的学生 MLP 即为最终的 GLNN,所以 GLNN 在训练中享有图拓扑结构(grap...
拿GraphSAGE举例，内置了两种训练方法：有监督训练，比如我们知道每个节点的label，那么我们就可以把这个当成...
For a node vv in graph GG , the K−hopK−hop neighbors NK,spdv,GNv,GK,spd of vv based on shortest path distance kernel is the set of nodes that have the shortest path distance from node vv less than or equal to KK . We further denote Qk,spdv,GQv,Gk,spd as the set of ...
Graph Neural Network Library for PyTorch. Contribute to pyg-team/pytorch_geometric development by creating an account on GitHub.
如果把GNN应用在 图表示 的场景中,使用不动点理论并不合适。这主要是因为基于不动点的收敛会导致结点之间的隐藏状态间存在较多信息共享,从而导致结点的状态太过光滑(Over Smooth),并且属于结点自身的特征信息匮乏(Less Informative)。 下面这张来自维基百科[13]的图可以形象地解释什么是 Over Smooth,其中我们把整个布...
Graph-less neural networks: Teaching old mlps new tricks via distillation[C]// The Tenth International Conference on Learning Representations. 2022. [8] Chen Y, Bian Y, Xiao X, et al. On self-distilling graph neural network[J]. arXiv preprint arXiv:2011.02255, 2020. [9] C. Zhang, J....
2 GCN depends on the specific graph structure, GCN is less possible to train dynamic graph. It ...
5 LESS POWERFUL BUT STILL INTERESTING GNNS 接下来,我们研究一下不满足 Theorem 3 (单射)条件的 GNNs,包括 GCN,GraphSAGE。再从两个方面开展关于聚合函数 Eq4.1 的消融实验 用1-layer 的感知机而不采用 MLPs(单纯邻域节点线性求和作为聚合策略是否可行) ...
The Neural Equivariant Interatomic Potential (NequIP25) predicts both energy and forces utilizing E(3)-equivariant convolutions over geometric tensors. Evaluated on the MD17 data set its accuracy exceeds those of existing models while needing up to three orders of magnitude less training data. Due...