arXiv (Cornell University) · 2020 · 45 citations · 39 references
ComputingData ScienceKnowledge RepresentationMachine LearningStatistical LearningDeep LearningGraph TheoryGraph-based LearningNetwork InferenceNeural NetworksRepresentation LearningGradient DescentGraph Neural NetworksGraph Representation LearningGraph Structure LearningImplicit Differentiation
Graph Neural Networks (GNNs) are widely used deep learning models that learn meaningful representations from graph-structured data. Due to the finite nature of the underlying recurrent structure, current GNN methods may struggle to capture long-range dependencies in underlying graphs. To overcome this difficulty, we propose a graph learning framework, called Implicit Graph Neural Networks (IGNN), where predictions are based on the solution of a fixed-point equilibrium equation involving implicitly defined "state" vectors. We use the Perron-Frobenius theory to derive sufficient conditions that ensure well-posedness of the framework. Leveraging implicit differentiation, we derive a tractable projected gradient descent method to train the framework. Experiments on a comprehensive range of tasks show that IGNNs consistently capture long-range dependencies and outperform the state-of-the-art GNN models.
39
Chih-Chung Chang, Chih‐Jen Lin · ACM Transactions on Intelligent Systems and Technology · 2011 · 41.3K citations
The PageRank Citation Ranking : Bringing Order to the Web
Lawrence M. Page, Sergey Brin, Rajeev Motwani et al. · 1999 · 12.7K citations
Inductive Representation Learning on Large Graphs
William L. Hamilton, Rex Ying, Jure Leskovec · arXiv (Cornell University) · 2017 · 4.5K citations · Full text
Neural Message Passing for Quantum Chemistry
Justin Gilmer, Samuel S. Schoenholz, Patrick Riley et al. · arXiv (Cornell University) · 2017 · 3K citations · Full text