我们通过下图来说明我们的动机。 用户X和Y具有相似的特征,在异亲性、同质性和混合三个特征维度上也具有相同的局部协调性。特别地,对于第一个特征维度,X(或Y)与它的任何一个邻居都不完全相同。在第二个特征维度上,X(或Y)的所有邻居的行为都与X(或Y)的行为相同。X(或Y)的第三个特征维度与它的一些相邻维度...
这些被扰动的节点被认为是增广属性图中的异常。 Discriminative Edge Heterophily Contrastive Learning Network 如前所述,由于同质性假设,gnn存在过平滑问题,这使得获得异常节点的代表性表示具有挑战性。在正常视图和异常视图中,边缘鉴别器执行无监督的边缘识别。同时,由低通和高通gnn组成的双通道编码器利用判别结果学习具...
self-supervised-learning contrastive-learning heterophily graph-contrastive-learning graph-self-supervised-learning heterophily-graph Updated Nov 2, 2023 EdisonLeeeee / SpikeGCL Star 28 Code Issues Pull requests [ICLR 2024] Official implementation of Spiking Graph Contrastive Learning (0️⃣1️...
In addition, fraud nodes in the networks are usually surrounded by normal nodes that have been cheated. This inherently heterophilic structure plays an important role in AML. Therefore, the problem of heterophily in transaction networks is also a research priority....
(GraphACL), is easy to implement and does not rely on graph augmentations and homophily assumptions. We provide theoretical and empirical evidence that GraphACL can capture one-hop local neighborhood information and two-hop monophily similarity, which are both important for modeling heterophilic ...