Node Classification on Non-Homophilic (Heterophilic) Graphs

28 papers with code • 15 benchmarks • 15 datasets

There exists a non-trivial set of graphs where graph-aware models underperform their corresponding graph-agnostic models, e.g. SGC and GCN underperform MLP with 1 layer and 2 layers. Although still controversial, people believe the performance degradation results from heterophily, i.e. there exist much more inter-class edges than inner-class edges. This task aims to evaluate models designed for non-homophilic (heterophilic) datasets.


Use these libraries to find Node Classification on Non-Homophilic (Heterophilic) Graphs models and implementations

Most implemented papers

Graph Attention Networks

PetarV-/GAT ICLR 2018

We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations.

Semi-Supervised Classification with Graph Convolutional Networks

tkipf/pygcn 9 Sep 2016

We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs.

Inductive Representation Learning on Large Graphs

williamleif/GraphSAGE NeurIPS 2017

Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying protein functions.

Simplifying Graph Convolutional Networks

Tiiiger/SGC 19 Feb 2019

Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations.

Combining Label Propagation and Simple Models Out-performs Graph Neural Networks

CUAI/CorrectAndSmooth ICLR 2021

Graph Neural Networks (GNNs) are the predominant technique for learning over graphs.

Predict then Propagate: Graph Neural Networks meet Personalized PageRank

klicperajo/ppnp ICLR 2019

We utilize this propagation procedure to construct a simple model, personalized propagation of neural predictions (PPNP), and its fast approximation, APPNP.

Geom-GCN: Geometric Graph Convolutional Networks

graphdml-uiuc-jlu/geom-gcn ICLR 2020

From the observations on classical neural network and network geometry, we propose a novel geometric aggregation scheme for graph neural networks to overcome the two weaknesses.

Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs

GemsLab/H2GCN NeurIPS 2020

We investigate the representation power of graph neural networks in the semi-supervised node classification task under heterophily or low homophily, i. e., in networks where connected nodes may have different class labels and dissimilar features.

Simple and Deep Graph Convolutional Networks

chennnM/GCNII ICML 2020

We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques: {\em Initial residual} and {\em Identity mapping}.

MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing

samihaija/mixhop 30 Apr 2019

Existing popular methods for semi-supervised learning with Graph Neural Networks (such as the Graph Convolutional Network) provably cannot learn a general class of neighborhood mixing relationships.