ICLR 2019 accepted papers on Graph learning
18 of the 502 papers accepted at ICLR 2019 (3.6%) are on Graph learning, compared with 2.4% at ICLR 2018. They fall into 4 topics.
See ICLR 2019 in the interactive map
Submitting to ICLR? 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
GNN architectures · 7 papers
- Predict then Propagate: Graph Neural Networks meet Personalized PageRank (428 citations)
- How Powerful are Graph Neural Networks? (374 citations)
- LanczosNet: Multi-Scale Deep Graph Convolutional Networks (183 citations)
- Capsule Graph Neural Network (140 citations)
- Supervised Community Detection with Line Graph Neural Networks (119 citations)
- Invariant and Equivariant Graph Networks (98 citations)
- Graph Wavelet Neural Network (75 citations)
Knowledge and temporal graphs · 5 papers
- RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space (756 citations)
- DyRep: Learning Representations over Dynamic Graphs (224 citations)
- Structured Neural Summarization (160 citations)
- Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension (43 citations)
- Visual Semantic Navigation using Scene Priors (36 citations)
Graph self-supervised learning · 3 papers
- Deep Graph Infomax (321 citations)
- Generative Code Modeling with Graphs (72 citations)
- Learning Multimodal Graph-to-Graph Translation for Molecule Optimization (44 citations)
Graph algorithms and clustering · 3 papers
- Learning a SAT Solver from Single-Bit Supervision (183 citations)
- Large Scale Graph Learning From Smooth Signals (51 citations)
- Neural Graph Evolution: Towards Efficient Automatic Robot Design (33 citations)
