NeurIPS 2018 accepted papers on Graph learning
32 of the 1,008 papers accepted at NeurIPS 2018 (3.2%) are on Graph learning, compared with 2.8% at NeurIPS 2017. They fall into 4 topics.
See NeurIPS 2018 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 · 16 papers
- DAGs with NO TEARS: Continuous Optimization for Structure Learning (217 citations)
- Watch Your Step: Learning Node Embeddings via Graph Attention (140 citations)
- Automatic differentiation in ML: Where we are and where we should be going (45 citations)
- RetGK: Graph Kernels based on Return Probabilities of Random Walks (37 citations)
- Contextual Stochastic Block Models (28 citations)
- Generalizing Graph Matching beyond Quadratic Assignment Model (28 citations)
- Practical Methods for Graph Two-Sample Testing (24 citations)
- Binary Rating Estimation with Graph Side Information (21 citations)
- Direct Estimation of Differences in Causal Graphs (11 citations)
- (Probably) Concave Graph Matching (9 citations)
- Learning to Multitask (9 citations)
- Experimental Design for Cost-Aware Learning of Causal Graphs (5 citations)
and 4 more in the interactive map.
Knowledge and temporal graphs · 6 papers
- SimplE Embedding for Link Prediction in Knowledge Graphs (393 citations)
- Symbolic Graph Reasoning Meets Convolutions (126 citations)
- Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction (101 citations)
- Embedding Logical Queries on Knowledge Graphs (59 citations)
- Expanding Holographic Embeddings for Knowledge Completion (19 citations)
- LinkNet: Relational Embedding for Scene Graph (6 citations)
GNN architectures · 5 papers
- Hierarchical Graph Representation Learning with Differentiable Pooling (882 citations)
- Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search (312 citations)
- Link Prediction Based on Graph Neural Networks (280 citations)
- Adaptive Sampling Towards Fast Graph Representation Learning (225 citations)
- Mean-field theory of graph neural networks in graph partitioning (28 citations)
Graph self-supervised learning · 5 papers
- Constrained Graph Variational Autoencoders for Molecule Design (330 citations)
- Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation (243 citations)
- Diffusion Maps for Textual Network Embedding (18 citations)
- Bayesian Semi-supervised Learning with Graph Gaussian Processes (17 citations)
- Constructing Deep Neural Networks by Bayesian Network Structure Learning (14 citations)
