ICLR 2020 accepted papers on Graph learning
49 of the 687 papers accepted at ICLR 2020 (7.1%) are on Graph learning, compared with 3.6% at ICLR 2019. They fall into 4 topics.
See ICLR 2020 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 · 22 papers
- DropEdge: Towards Deep Graph Convolutional Networks on Node Classification (649 citations)
- Geom-GCN: Geometric Graph Convolutional Networks (429 citations)
- Directional Message Passing for Molecular Graphs (349 citations)
- GraphSAINT: Graph Sampling Based Inductive Learning Method (328 citations)
- PairNorm: Tackling Oversmoothing in GNNs (225 citations)
- Graph Neural Networks Exponentially Lose Expressive Power for Node Classification (185 citations)
- Strategies for Pre-training Graph Neural Networks (180 citations)
- A Fair Comparison of Graph Neural Networks for Graph Classification (116 citations)
- Global Relational Models of Source Code (98 citations)
- What Can Neural Networks Reason About? (97 citations)
- The Logical Expressiveness of Graph Neural Networks (95 citations)
- Adaptive Structural Fingerprints for Graph Attention Networks (52 citations)
and 10 more in the interactive map.
Knowledge and temporal graphs · 12 papers
- Composition-based Multi-Relational Graph Convolutional Networks (136 citations)
- You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings (104 citations)
- HOPPITY: LEARNING GRAPH TRANSFORMATIONS TO DETECT AND FIX BUGS IN PROGRAMS (90 citations)
- LambdaNet: Probabilistic Type Inference using Graph Neural Networks (63 citations)
- Inductive Matrix Completion Based on Graph Neural Networks (31 citations)
- Inductive representation learning on temporal graphs (29 citations)
- Abstract Diagrammatic Reasoning with Multiplex Graph Networks (24 citations)
- Differentiable learning of numerical rules in knowledge graphs (22 citations)
- Automated Relational Meta-learning (20 citations)
- Probability Calibration for Knowledge Graph Embedding Models (15 citations)
- Dynamically Pruned Message Passing Networks for Large-scale Knowledge Graph Reasoning (11 citations)
- LEARNING EXECUTION THROUGH NEURAL CODE FUSION (1 citation)
Graph self-supervised learning · 8 papers
- GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation (201 citations)
- InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization (146 citations)
- StructPool: Structured Graph Pooling via Conditional Random Fields (109 citations)
- Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation (102 citations)
- On the Equivalence between Positional Node Embeddings and Structural Graph Representations (23 citations)
- Graph inference learning for semi-supervised classification (18 citations)
- FEW-SHOT LEARNING ON GRAPHS VIA SUPER-CLASSES BASED ON GRAPH SPECTRAL MEASURES (16 citations)
- Inductive and Unsupervised Representation Learning on Graph Structured Objects (15 citations)
Graph algorithms and clustering · 7 papers
- Deep Graph Matching Consensus (52 citations)
- Learning deep graph matching with channel-independent embedding and Hungarian attention (43 citations)
- Reinforced Genetic Algorithm Learning for Optimizing Computation Graphs (36 citations)
- GraphZoom: A Multi-level Spectral Approach for Accurate and Scalable Graph Embedding (14 citations)
- Order Learning and Its Application to Age Estimation (9 citations)
- GLAD: Learning Sparse Graph Recovery (3 citations)
- Low-dimensional statistical manifold embedding of directed graphs
