NeurIPS 2017 accepted papers on Graph learning
19 of the 688 papers accepted at NeurIPS 2017 (2.8%) are on Graph learning, compared with 2.6% at NeurIPS 2016. They fall into 3 topics.
See NeurIPS 2017 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 · 13 papers
- Learning Combinatorial Optimization Algorithms over Graphs (1,066 citations)
- Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks (259 citations)
- Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network (218 citations)
- Hunt For The Unique, Stable, Sparse And Fast Feature Learning On Graphs (86 citations)
- Learning A Structured Optimal Bipartite Graph for Co-Clustering (86 citations)
- Premise Selection for Theorem Proving by Deep Graph Embedding (75 citations)
- Experimental Design for Learning Causal Graphs with Latent Variables (33 citations)
- Graph Matching via Multiplicative Update Algorithm (19 citations)
- Near-Optimal Edge Evaluation in Explicit Generalized Binomial Graphs (13 citations)
- From which world is your graph (6 citations)
- Improved Graph Laplacian via Geometric Self-Consistency (6 citations)
- On clustering network-valued data
and 1 more in the interactive map.
Graph self-supervised learning · 4 papers
- Inductive Representation Learning on Large Graphs (4,474 citations)
- Deep Learning with Topological Signatures (100 citations)
- Learning Graph Representations with Embedding Propagation (78 citations)
- PRUNE: Preserving Proximity and Global Ranking for Network Embedding (57 citations)
