Graph learning: research map
Graph neural networks, knowledge graphs and graph algorithms.
4,536 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026), in 4 topics. Within all five venues, its share shrank from 4.8% in 2023–24 to 3.5% in 2025–26 (1,272 → 1,576 papers at ICML, NeurIPS, CVPR and AAAI, the venues with data for all four years).
Explore Graph learning in the interactive map
Topics
- GNN architectures · 1,471 papers
GNN generalization theory, Simple and scalable GNNs, Robustness, privacy, and fairness of GNNs - Graph self-supervised learning · 1,274 papers
Semi-supervised node representation learning, Heterophily and imbalance on graphs, LLMs and graph foundation models - Knowledge and temporal graphs · 974 papers
Graph reasoning for visual recognition, Graph-based dialog systems, Heterogeneous graph learning - Graph algorithms and clustering · 817 papers
Neural combinatorial optimization on graphs, Graph comparison and random features, Graph embedding and spectral sparsification
Most cited papers in Graph learning
- Graph Attention Networks (ICLR 2018 · 9,105 citations)
- Semi-Supervised Classification with Graph Convolutional Networks (ICLR 2017 · 7,975 citations)
- Inductive Representation Learning on Large Graphs (NeurIPS 2017 · 4,474 citations)
- Neural Message Passing for Quantum Chemistry (ICML 2017 · 3,844 citations)
- Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition (CVPR 2019 · 2,091 citations)
- Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering (NeurIPS 2016 · 1,699 citations)
- Actional-Structural Graph Convolutional Networks for Skeleton-Based Action Recognition (CVPR 2019 · 1,272 citations)
- Simplifying Graph Convolutional Networks (ICML 2019 · 1,272 citations)
- Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition (CVPR 2020 · 1,219 citations)
- Structural-RNN: Deep Learning on Spatio-Temporal Graphs (CVPR 2016 · 1,151 citations)
- Learning Combinatorial Optimization Algorithms over Graphs (NeurIPS 2017 · 1,066 citations)
- Graph Contrastive Learning with Augmentations (NeurIPS 2020 · 859 citations)