Enhancing Distribution and Label Consistency for Graph Out-of-Distribution Generalization
Not on the map. Why?
Abstract (arXiv)
To deal with distribution shifts in graph data, various graph out-of-distribution (OOD) generalization techniques have been recently proposed. These methods often employ a two-step strategy that first creates augmented environments and subsequently identifies invariant subgraphs to improve generalizability. Nevertheless, this approach could be suboptimal from the perspective of consistency. First, the process of augmenting environments by altering the graphs while preserving labels may lead to graphs that are not realistic or meaningfully related to the origin distribution, thus lacking distribution consistency. Second, the extracted subgraphs are obtained from directly modifying graphs, and may not necessarily maintain a consistent predictive relationship with their labels, thereby impacting label consistency. In response to these challenges, we introduce an innovative approach that aims to enhance these two types of consistency for graph OOD generalization. We propose a modifier to obtain both augmented and invariant graphs in a unified manner. With the augmented graphs, we enrich the training data without compromising the integrity of label-graph relationships. The label consistency enhancement in our framework further preserves the supervision information in the invariant graph. We conduct extensive experiments on real-world datasets to demonstrate the superiority of our framework over other state-of-the-art baselines.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 48 of its 62 references that are in the map. First posted on arXiv 7 Jan 2025.
Builds on
48 of 62 references.
References · 48
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2018How Powerful are Graph Neural Networks?cited by 4,355
- 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
- 2019Invariant Risk Minimizationcited by 1,832
- 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
- 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
- 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
36 more
- 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
- 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
- 2018Recognition in Terra Incognitacited by 655
- 2013Domain Generalization via Invariant Feature Representationcited by 622
- 2017One pixel attack for fooling deep neural networkscited by 579
- 2020Parameterized Explainer for Graph Neural Networkcited by 423
- 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 406
- 2015Return of Frustratingly Easy Domain Adaptationcited by 389
- 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 332
- 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 328
- 2022Discovering Invariant Rationales for Graph Neural Networkscited by 186
- 2019Graph Neural Networks with convolutional ARMA filterscited by 185
- 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
- 2019Understanding Attention and Generalization in Graph Neural Networkscited by 169
- 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
- 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
- 2017Invariant Causal Prediction for Nonlinear Modelscited by 140
- 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 140
- 2020Invariant Rationalizationcited by 131
- 2018Invariance, Causality and Robustnesscited by 123
- 2018Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttimecited by 122
- 2021Causal Attention for Interpretable and Generalizable Graph Classificationcited by 108
- 2019Meta-GNN: On Few-shot Node Classification in Graph Meta-learningcited by 105
- 2015Inferring Networks of Substitutable and Complementary Productscited by 91
- 2020Graph Prototypical Networks for Few-shot Learning on Attributed Networkscited by 90
- 2022Debiasing Graph Neural Networks via Learning Disentangled Causal Substructurecited by 83
- 2022DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotationscited by 54
- 2023Does Invariant Graph Learning via Environment Augmentation Learn Invariance?cited by 42
- 2021Graph Few-shot Class-incremental Learningcited by 40
- 2018Robust Optimization over Multiple Domainscited by 34
- 2023Mind the Label Shift of Augmentation-based Graph OOD Generalizationcited by 34
- 2022Graph Few-shot Learning with Task-specific Structurescited by 26
- 2022Adversarial Weight Perturbation Improves Generalization in Graph Neural Networkscited by 21
- 2023Few-shot Node Classification with Extremely Weak Supervisioncited by 14
- 2023Contrastive Meta-Learning for Few-shot Node Classificationcited by 11
- 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
Built on by
Citing papers per year: 2025: 2.
2 papers.