README.md

🚀 Awesome-Graph-OOD-Learning

This repository for the paper 📘: A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptation. The README file here maintains a list of papers on graph out-of-distribution learning, covering three primary scenarios: graph OOD generalization, training-time graph OOD adaptation, and test-time graph OOD adaptation.

Check out our existing survey 📄: Beyond Generalization: A Survey of Out-Of-Distribution Adaptation on Graphs, which contains a list of papers on graph out-of-distribution adaptation.

If you find this repository helpful to your work, please kindly star it and cite our survey paper as follows:

@article{zhang2024surveygraph,
      title={A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptation}, 
      author={Kexin Zhang and Shuhan Liu and Song Wang and Weili Shi and Chen Chen and Pan Li and Sheng Li and Jundong Li and Kaize Ding},
      journal={arXiv preprint arXiv:2410.19265},
      year={2024}
}

🤗 Contributions to update new resources and articles are very welcome!

❖ Contents

• Graph OOD Generalization
  • Model-centric Approaches
  • Data-centric Approaches
• Training-time Graph OOD Adaptation
  • Model-centric Approaches
  • Data-centric Approaches
• Test-time Graph OOD Adaptation
  • Model-centric Approaches
  • Data-centric Approaches
• Transferability evaluation

❖ Graph OOD Generalization

Model-centric Approaches

Name	Category	Paper	Code
DIR	Invariant Representation Learning	[ICLR 2022] Discovering invariant rationales for graph neural networks	Code
GIL	Invariant Representation Learning	[NeurIPS 2022] Learning invariant graph representations for out-of-distribution generalization	[N/A]
GSAT	Invariant Representation Learning	[ICML 2022] Interpretable and generalizable graph learning via stochastic attention mechanism	Code
IS-GIB	Invariant Representation Learning	[TKDE 2023] Individual and structural graph information bottlenecks for out-of-distribution generalization	Code
MARIO	Invariant Representation Learning	[TheWebConf 2024] Mario: Model agnostic recipe for improving ood generalization of graph contrastive learning	Code
DIVE	Invariant Representation Learning	[KDD 2024] DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalization	[N/A]
CAP	Invariant Representation Learning	[arXiv] CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks	[N/A]
GraphAT	Invariant Representation Learning	[TKDE 2019] Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure	Code
GNN-DRO	Invariant Representation Learning	[arXiv] Distributionally robust semi-supervised learning over graphs	[N/A]
WT-AWP	Invariant Representation Learning	[AAAI 2023] Adversarial weight perturbation improves generalization in graph neural networks	[N/A]
DisenGCN	Invariant Representation Learning	[ICML 2019] Disentangled graph convolutional networks	[N/A]
IPGDN	Invariant Representation Learning	[AAAI 2020] Independence promoted graph disentangled networks	[N/A]
FactorGCN	Invariant Representation Learning	[NeurIPS 2020] Factorizable graph convolutional networks	Code
NED-VAE	Invariant Representation Learning	[KDD 2020] Interpretable deep graph generation with node-edge co-disentanglement	Code
DGCL	Invariant Representation Learning	[NeurIPS 2021] Disentangled contrastive learning on graphs	[N/A]
IDGCL	Invariant Representation Learning	[TKDE 2022] Disentangled graph contrastive learning with independence promotion	[N/A]
I-DIDA	Invariant Representation Learning	[arXiv] Out-of-distribution generalized dynamic graph neural network with disentangled intervention and invariance promotion	[N/A]
L2R-GNN	Invariant Representation Learning	[AAAI 2024] Learning to reweight for generalizable graph neural network	[N/A]
OOD-GNN	Invariant Representation Learning	[TKDE 2022] OOD-GNN: Out-of-Distribution Generalized Graph Neural Network	[N/A]
EQuAD	Invariant Representation Learning	[ICML 2024] Empowering Graph Invariance Learning with Deep Spurious Infomax	Code
DIDA	Invariant Representation Learning	[NeurIPS 2022] Dynamic graph neural networks under spatio-temporal distribution shift	Code
EAGLE	Invariant Representation Learning	[NeurIPS 2024] Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization	Code
CauSTG	Invariant Representation Learning	[KDD 2023] Maintaining the status quo: Capturing invariant relations for ood spatiotemporal learning	Code
STONE	Invariant Representation Learning	[KDD 2024] STONE: A Spatio-temporal OOD Learning Framework Kills Both Spatial and Temporal Shifts	Code
E-invariant GR	Causality-based Learning	[ICML 2021] Size-invariant graph representations for graph classification extrapolations	Code
CIGA	Causality-based Learning	[NeurIPS 2022] Learning causally invariant representations for out-of-distribution generalization on graphs	Code
CAL	Causality-based Learning	[KDD 2022] Causal attention for interpretable and generalizable graph classification	Code
DisC	Causality-based Learning	[NeurIPS 2022] Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure	Code
GALA	Causality-based Learning	[NeurIPS 2024] Does invariant graph learning via environment augmentation learn invariance?	Code
LECI	Causality-based Learning	[NeurIPS 2024] Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization	Code
StableGNN	Causality-based Learning	[TPAMI 2023] Generalizing graph neural networks on out-of-distribution graphs	Code
Pretraining-GNN	Graph Self-supervised Learning	[ICLR 2020] Strategies for pre-training graph neural networks	[N/A]
PATTERN	Graph Self-supervised Learning	[ICML 2021] From local structures to size generalization in graph neural networks	[N/A]
OOD-GCL	Graph Self-supervised Learning	[ICML 2024] Disentangled Graph Self-supervised Learning for Out-of-Distribution Generalization	[N/A]
GPPT	Graph Self-supervised Learning	[KDD 2022] GPPT: Graph Pre-training and Prompt Tuning to Generalize Graph Neural Networks	Code
GPF	Graph Self-supervised Learning	[NeurIPS 2024] Universal prompt tuning for graph neural networks	Code
GraphControl	Graph Self-supervised Learning	[TheWebConf 2024] GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learning	Code

Data-centric Approaches

Name	Category	Paper	Code
AIA	Graph Data Augmentation	[NeurIPS 2023] Unleashing the power of graph data augmentation on covariate distribution shift	Code
G-Splice	Graph Data Augmentation	[arXiv] Graph structure and feature extrapolation for out-of-distribution generalization	[N/A]
LiSA	Graph Data Augmentation	[CVPR 2023] Mind the Label Shift of Augmentation-based Graph OOD Generalization	Code
DLG	Graph Data Augmentation	[[ICDM 2024] Enhancing Distribution and Label Consistency for Graph Out-of-Distribution Generalization]	[N/A]
Pattern-PT	Graph Data Augmentation	[ICML 2021] From local structures to size generalization in graph neural networks	[N/A]
P-gMPNN	Graph Data Augmentation	[NeurIPS 2022] OOD link prediction generalization capabilities of message-passing GNNs in larger test graphs	Code
GraphMix	Graph Data Augmentation	[AAAI 2021] Graphmix: Improved training of gnns for semi-supervised learning	Code
G-Mixup	Graph Data Augmentation	[TheWebConf 2021] Mixup for node and graph classification	[N/A]
$\mathcal{G}$-Mixup	Graph Data Augmentation	[ICML 2022] G-mixup: Graph data augmentation for graph classification	Code
OOD-GMixup	Graph Data Augmentation	[TKDE 2024] Graph out-of-distribution generalization with controllable data augmentation	[N/A]
GREA	Distribution Augmentation	[KDD 2022] Graph rationalization with environment-based augmentations	Code
EERM	Distribution Augmentation	[ICLR 2022] Handling distribution shifts on graphs: An invariance perspective	Code
FLOOD	Distribution Augmentation	[KDD 2023] FLOOD: A Flexible Invariant Learning Framework for Out-of-Distribution Generalization on Graphs	[N/A]
DPS	Distribution Augmentation	[arXiv] Finding Diverse and Predictable Subgraphs for Graph Domain Generalization	[N/A]
MoleOOD	Distribution Augmentation	[NeurIPS 2022] Learning substructure invariance for out-of-distribution molecular representations	Code
ERASE	Distribution Augmentation	[CIKM 2024] ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance	Code
IGM	Distribution Augmentation	[AAAI 2024] Graph invariant learning with subgraph co-mixup for out-of-distribution generalization	Code

❖ Training-time Graph OOD Adaptation

Model-centric Approaches

Name	Category	Paper	Code
DAGNN	Invariant Representation Learning	[ICDM 2019] Domain-Adversarial Graph Neural Networks for Text Classification	[N/A]
DANE	Invariant Representation Learning	[ICJAI 2019] DANE: Domain Adaptive Network Embedding	Unofficial
CDNE	Invariant Representation Learning	[TNNLS 2020] Network Together: Node Classification via Cross-Network Deep Network Embedding	Code
ACDNE	Invariant Representation Learning	[AAAI 2020] Adversarial Deep Network Embedding for Cross-network Node Classification	Code
UDA-GCN	Invariant Representation Learning	[TheWebConf 2020] Unsupervised Domain Adaptive Graph Convolutional Networks	Code
DGDA	Invariant Representation Learning	[TKDD 2024] Graph domain adaptation: A generative view.	Code
SR-GNN	Invariant Representation Learning	[NeurIPS 2021] Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data	Code
ASN	Invariant Representation Learning	[CIKM 2021] Adversarial separation network for cross-network node classification	Code
AdaGCN	Invariant Representation Learning	[TKDE 2022] Graph transfer learning via adversarial domain adaptation with graph convolution	Code
GraphAE	Invariant Representation Learning	[TKDE 2023] Learning adaptive node embeddings across graphs	[N/A]
GRADE	Invariant Representation Learning	[AAAI 2023] Non-iid transfer learning on graphs	Code
JHGDA	Invariant Representation Learning	[CIKM 2023] Improving graph domain adaptation with network hierarchy	Code
SGDA	Invariant Representation Learning	[ICJAI 2023] Semi-supervised Domain Adaptation in Graph Transfer Learning	Code
MTDF	Invariant Representation Learning	[ICDE 2024] Multi-View Teacher with Curriculum Data Fusion for Robust Unsupervised Domain Adaptation	[N/A]
SDA	Invariant Representation Learning	[AAAI 2024] Open-set graph domain adaptation via separate domain alignment	[N/A]
JDA-GCN	Invariant Representation Learning	[ICJAI 2024] Joint domain adaptive graph convolutional network	[N/A]
HC-GST	Invariant Representation Learning	[CIKM 2024] HC-GST: Heterophily-aware Distribution Consistency based Graph Self-training	[N/A]
DREAM	Invariant Representation Learning	[ICLR 2024] DREAM: Dual structured exploration with mixup for open-set graph domain adaption	[N/A]
SelMAG	Invariant Representation Learning	[KDD 2024] Multi-source Unsupervised Domain Adaptation on Graphs with Transferability Modeling	[N/A]
SRNC	Concept-shift Aware Representation Learning	[NeurIPS 2022] Shift-Robust Node Classification via Graph Clustering Co-training	[N/A]
StruRW	Concept-shift Aware Representation Learning	[ICML 2023] Structural re-weighting improves graph domain adaptation	Code
Pair-Align	Concept-shift Aware Representation Learning	[ICML 2024] Pairwise Alignment Improves Graph Domain Adaptation	Code
GCONDA++	Concept-shift Aware Representation Learning	[arXiv] Explaining and Adapting Graph Conditional Shift	[N/A]
KDGA	Model Regularization	[NeurIPS 2022] Knowledge distillation improves graph structure augmentation for graph neural networks	Code
SS/MFR-Reg	Model Regularization	[ICLR 2023] Graph domain adaptation via theory-grounded spectral regularization	Code
KTGNN	Model Regularization	[TheWebConf 2023] Predicting the Silent Majority on Graphs: Knowledge Transferable Graph Neural Network	Code
A2GNN	Model Regularization	[AAAI 2024] Rethinking propagation for unsupervised graph domain adaptation	Code

Data-centric Approaches

Name	Category	Paper	Code
IW	Instance Weighting	[TheWebConf 2013] Predicting positive and negative links in signed social networks by transfer learning	[N/A]
NES-TL	Instance Weighting	[TNSE 2020] Nes-tl: Network embedding similarity-based transfer learning	[N/A]
RSS-GNN	Instance Weighting	[BIBM 2022] Reinforced Sample Selection for Graph Neural Networks Transfer Learning	[N/A]
DR-GST	Instance Weighting	[TheWebConf 2022] Confidence may cheat: Self-training on graph neural networks under distribution shift	Code
FakeEdge	Graph Data Augmentation	[LoG 2022] Fakeedge: Alleviate dataset shift in link prediction	Code
Bridged-GNN	Graph Data Augmentation	[CIKM 2023] Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfer	Code
DC-GST	Graph Data Augmentation	[WSDM 2024] Distribution consistency based self-training for graph neural networks with sparse labels	[N/A]
LTLP	Graph Data Augmentation	[KDD 2024] Optimizing Long-tailed Link Prediction in Graph Neural Networks through Structure Representation Enhancement	[N/A]

❖ Test-time Graph OOD Adaptation

Model-centric Approaches

Name	Category	Paper	Code
GraphControl	Semi-supervised Fine-tuning	[arXiv] GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learning	[N/A]
G-Adapter	Semi-supervised Fine-tuning	[AAAI 2024] G-Adapter: Towards Structure-Aware Parameter-Effcient Transfer Learning for Graph Transformer Networks	[N/A]
AdapterGNN	Semi-supervised Fine-tuning	[AAAI 2024] Adaptergnn: Parameter-efficient fine-tuning improves generalization in gnns	Code
PROGRAM	Semi-supervised Fine-tuning	[ICLR 2024] PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time Adaptation	[N/A]
SOGA	Self-supervised Adaptation	[WSDM 2024] Source free unsupervised graph domain adaptation	Code
GAPGC	Self-supervised Adaptation	[ICML 2022] GraphTTA: Test Time Adaptation on Graph Neural Networks	[N/A]
GT3	Self-supervised Adaptation	[arXiv] Test-time training for graph neural networks	[N/A]
GraphGLOW	Self-supervised Adaptation	[KDD 2023] GraphGLOW: Universal and Generalizable Structure Learning for Graph Neural Networks	Code
RNA	Self-supervised Fine-tuning	[IJCAI 2024] Rank and Align: Towards Effective Source-free Graph Domain Adaptation	[N/A]

Data-centric Approaches

Name	Category	Paper	Code
FRGNN	Feature Reconstruction	[arXiv] FRGNN: Mitigating the Impact of Distribution Shift on Graph Neural Networks via Test-Time Feature Reconstruction	[N/A]
GTRANS	Graph Data Augmentation	[ICLR 2023] Empowering graph representation learning with test-time graph transformation	Code
GraphCTA	Graph Data Augmentation	[TheWebConf 2024] Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation	Code
SGOOD	Graph Data Augmentation	[arXiv] SGOOD: Substructure-enhanced Graph-Level Out-of-Distribution Detection	[N/A]
GALA	Graph Data Augmentation	[TPAMI 2024] GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation	Code

❖ Related: Transferability evaluation

Name	Paper	Code
EGI	[NeurIPS 2021] Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization	Code
WNN	[NeurIPS 2020] Graphon Neural Networks and the Transferability of Graph Neural Networks	[N/A]
TMD	[NeurIPS 2022] Tree Mover’s Distance: Bridging Graph Metrics and Stability of Graph Neural Networks	Code
W2PGNN	[KDD 2023] When to Pre-Train Graph Neural Networks? From Data Generation Perspective!	Code