的时候, 我们称这个图是偏 homophily 的, 否则则这个图是偏 heterophily 的. 注意: heterophily 和常说的 Heterogeneity (异构图) 有点像, 后者描述的是一个图的结点的 type 不一致 (≥2≥2), 比如一个图中存在 (users, watch, movies) 的关系. 前者描述了 group 的一个性质, 显然当 h→1
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective DesignsJiong ZhuYujun YanLingxiao ZhaoDanai Koutra
Graph neural networks (GNNs) have been intensively studied in various real-world tasks. However, the homophily assumption of GNNs' aggregation function limits their representation learning ability in heterophily graphs. In this paper, we shed light on the path level patterns in graphs that can ...
【阿里&北大】Meta-Weight Graph Neural Network: Push the Limits Beyond Global Homophily 一句话介绍传统图网络中的聚合函数在不同node之间是share parameters的,这种方式可以有效建模图节点的同质性( ho…
Keywords: Graph Clustering, HomophilyIntroduction 虽然异质性方法提高了gnn在一些下游任务,存在两个关键问题: 1)定制网络的训练,自适应过滤器的学习和图重组方法依赖于标记样本,这使得它们不适用于聚类任务…
Paper tables with annotated results for Unifying over-smoothing and over-squashing in graph neural networks: A physics informed approach and beyond
PathNet is a structure-aware path aggregation graph neural network that can deal with both homophily and heterophily graphs. This implementation of PathNet is based onPytorch GeometricAPI. Building the Project splits: need to unzipped, contains the split data of "Cora, Cornell, Pubmed and Citese...
Graph neural networks (GNNs) have been extensively studied for prediction tasks on graphs. Aspointed out by recent studies, most GNNs assume local homophily, i.e., strong similarities in localneighborhoods. This assumption however limits the generalizability power of GNNs. To address thislimitation,...
However, existing graph representation learning approaches are designed mainly under the node homophily assumption: connected nodes tend to have similar labels and optimize performance on node-centric downstream tasks. Their design is apparently against the task-agnostic principle and generally suffers poor...