NeurIPS 2019 accepted papers on Graph learning
76 of the 1,429 papers accepted at NeurIPS 2019 (5.3%) are on Graph learning, compared with 3.2% at NeurIPS 2018. They fall into 4 topics.
See NeurIPS 2019 in the interactive map
Submitting to NeurIPS? 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 · 33 papers
- Exact Combinatorial Optimization with Graph Convolutional Neural Networks (249 citations)
- D-VAE: A Variational Autoencoder for Directed Acyclic Graphs (86 citations)
- End to end learning and optimization on graphs (61 citations)
- Wasserstein Weisfeiler-Lehman Graph Kernels (60 citations)
- GOT: An Optimal Transport framework for Graph comparison (54 citations)
- DiskANN: Fast Accurate Billion-point Nearest Neighbor Search on a Single Node (46 citations)
- Retrosynthesis Prediction with Conditional Graph Logic Network (43 citations)
- (Nearly) Efficient Algorithms for the Graph Matching Problem on Correlated Random Graphs (40 citations)
- Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching (35 citations)
- Combinatorial Bayesian Optimization using the Graph Cartesian Product (34 citations)
- Exploring Algorithmic Fairness in Robust Graph Covering Problems (33 citations)
- A Unifying Framework for Spectrum-Preserving Graph Sparsification and Coarsening (32 citations)
and 21 more in the interactive map.
GNN architectures · 19 papers
- GNNExplainer: Generating Explanations for Graph Neural Networks (687 citations)
- Graph Transformer Networks (505 citations)
- Hyperbolic Graph Convolutional Neural Networks (262 citations)
- Diffusion Improves Graph Learning (172 citations)
- Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks (151 citations)
- Universal Invariant and Equivariant Graph Neural Networks (130 citations)
- Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels (126 citations)
- Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks (112 citations)
- Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology (81 citations)
- Hyperbolic Graph Neural Networks (77 citations)
- Understanding Attention and Generalization in Graph Neural Networks (55 citations)
- Stability of Graph Scattering Transforms (38 citations)
and 7 more in the interactive map.
Graph self-supervised learning · 13 papers
- Efficient Graph Generation with Graph Recurrent Attention Networks (168 citations)
- N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules (104 citations)
- Graph Normalizing Flows (69 citations)
- HyperGCN: A New Method For Training Graph Convolutional Networks on Hypergraphs (60 citations)
- Conditional Structure Generation through Graph Variational Generative Adversarial Nets (57 citations)
- Learning metrics for persistence-based summaries and applications for graph classification (54 citations)
- Learning to Propagate for Graph Meta-Learning (48 citations)
- Graph Agreement Models for Semi-Supervised Learning (42 citations)
- A Flexible Generative Framework for Graph-based Semi-supervised Learning (39 citations)
- vGraph: A Generative Model for Joint Community Detection and Node Representation Learning (17 citations)
- Rethinking Kernel Methods for Node Representation Learning on Graphs (10 citations)
- Graph-Based Semi-Supervised Learning with Non-ignorable Non-response (8 citations)
and 1 more in the interactive map.
Knowledge and temporal graphs · 11 papers
- Quaternion Knowledge Graph Embeddings (281 citations)
- Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks (113 citations)
- Probabilistic Logic Neural Networks for Reasoning (97 citations)
- Variational Graph Recurrent Neural Networks (96 citations)
- DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs (61 citations)
- Recurrent Space-time Graph Neural Networks (30 citations)
- Multi-relational Poincaré Graph Embeddings (29 citations)
- STREETS: A Novel Camera Network Dataset for Traffic Flow (26 citations)
- Embedding Symbolic Knowledge into Deep Networks (4 citations)
- Graph Structured Prediction Energy Networks (2 citations)
- Neural Relational Inference with Fast Modular Meta-learning
