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.
Benchmarks
These leaderboards are used to track progress in Node Classification on Non-Homophilic (Heterophilic) Graphs
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Node Classification on Non-Homophilic (Heterophilic) Graphs models and implementationsDatasets
Pubmed
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
•
•
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
•
•
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
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
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
•
•
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.
