ICML 2019 accepted papers on Graph learning
36 of the 774 papers accepted at ICML 2019 (4.7%) are on Graph learning, compared with 2.2% at ICML 2018. They fall into 4 topics.
See ICML 2019 in the interactive map
Submitting to ICML? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Graph algorithms and clustering · 12 papers
- Graph Matching Networks for Learning the Similarity of Graph Structured Objects (298 citations)
- DAG-GNN: DAG Structure Learning with Graph Neural Networks (154 citations)
- Optimal Transport for structured data with application on graphs (136 citations)
- Gromov-Wasserstein Learning for Graph Matching and Node Embedding (102 citations)
- GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects (35 citations)
- Hyperbolic Disk Embeddings for Directed Acyclic Graphs (27 citations)
- Random Walks on Hypergraphs with Edge-Dependent Vertex Weights (21 citations)
- Active Learning with Disagreement Graphs (9 citations)
- Learning to Route in Similarity Graphs (4 citations)
- Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications (2 citations)
- Graph Resistance and Learning from Pairwise Comparisons (1 citation)
- Improved Dynamic Graph Learning through Fault-Tolerant Sparsification (1 citation)
GNN architectures · 10 papers
- Simplifying Graph Convolutional Networks (1,272 citations)
- Self-Attention Graph Pooling (370 citations)
- MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing (268 citations)
- Learning Discrete Structures for Graph Neural Networks (181 citations)
- GMNN: Graph Markov Neural Networks (160 citations)
- Position-aware Graph Neural Networks (78 citations)
- Circuit-GNN: Graph Neural Networks for Distributed Circuit Design (70 citations)
- Relational Pooling for Graph Representations (37 citations)
- Graph Element Networks: adaptive, structured computation and memory (21 citations)
- Recursive Sketches for Modular Deep Learning (1 citation)
Graph self-supervised learning · 9 papers
- Graph U-Nets (202 citations)
- Disentangled Graph Convolutional Networks (134 citations)
- Compositional Fairness Constraints for Graph Embeddings (116 citations)
- Lorentzian Distance Learning for Hyperbolic Representations (43 citations)
- A Persistent Weisfeiler-Lehman Procedure for Graph Classification (41 citations)
- Graphite: Iterative Generative Modeling of Graphs (35 citations)
- Stochastic Blockmodels meet Graph Neural Networks (16 citations)
- Graph Convolutional Gaussian Processes (9 citations)
- Geometric Scattering for Graph Data Analysis (6 citations)
Knowledge and temporal graphs · 5 papers
- Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs (105 citations)
- LatentGNN: Learning Efficient Non-local Relations for Visual Recognition (63 citations)
- Open Vocabulary Learning on Source Code with a Graph-Structured Cache (20 citations)
- Graph Neural Network for Music Score Data and Modeling Expressive Piano Performance (19 citations)
- Distributed, Egocentric Representations of Graphs for Detecting Critical Structures (8 citations)
