Size-Invariant Graph Representations for Graph Classification Extrapolations
arXiv:2103.05045
Abstract
In general, graph representation learning methods assume that the train and test data come from the same distribution. In this work we consider an underexplored area of an otherwise rapidly developing field of graph representation learning: The task of out-of-distribution (OOD) graph classification, where train and test data have different distributions, with test data unavailable during training. Our work shows it is possible to use a causal model to learn approximately invariant representations that better extrapolate between train and test data. Finally, we conclude with synthetic and real-world dataset experiments showcasing the benefits of representations that are invariant to train/test distribution shifts.
Accepted at ICML 2021
References in corpus (19)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Fast Graph Representation Learning with PyTorch Geometric
- Variational Graph Auto-Encoders
- Biological network comparison using graphlet degree distribution
- Interaction Networks for Learning about Objects, Relations and Physics
- Underspecification Presents Challenges for Credibility in Modern Machine Learning
- TUDataset: A collection of benchmark datasets for learning with graphs
- Neural Combinatorial Optimization with Reinforcement Learning
- Hyperbolic Graph Convolutional Neural Networks
- A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
- Hyperbolic Graph Neural Networks
- Causal Discovery from Changes
- Telling cause from effect in deterministic linear dynamical systems
- GraphCrop: Subgraph Cropping for Graph Classification
- Estimating Generalization under Distribution Shifts via Domain-Invariant Representations
- On the Equivalence Between Temporal and Static Graph Representations for Observational Predictions
- Heterogeneous Network Motifs
- Representation Learning of Graphs Using Graph Convolutional Multilayer Networks Based on Motifs
- Neural Networks for Learning Counterfactual G-Invariances from Single Environments