NeurIPS 2019 accepted papers by research area
1,429 papers were accepted at NeurIPS 2019 (+421 vs 2018). Here is how they split across 20 research areas, and which topics gained the most ground.
See NeurIPS 2019 in the interactive map
Submitting to NeurIPS? Checklist →
Research areas
| Area | Papers | Share | Change in share vs 2018 |
|---|---|---|---|
| Learning theory and algorithms | 279 | 19.5% | -0.9 pts |
| Probabilistic and scientific modeling | 198 | 13.9% | -2.4 pts |
| Optimization | 159 | 11.1% | steady |
| Architectures and efficiency | 127 | 8.9% | -0.6 pts |
| Reinforcement learning | 99 | 6.9% | steady |
| Label-efficient and robust learning | 95 | 6.6% | -0.6 pts |
| Bandits and online learning | 80 | 5.6% | +1.3 pts |
| Graph learning | 76 | 5.3% | +2.1 pts |
| Adversarial robustness and security | 52 | 3.6% | +0.4 pts |
| Image generation | 48 | 3.4% | -0.3 pts |
| Detection and segmentation | 33 | 2.3% | -0.4 pts |
| Multi-agent systems and games | 30 | 2.1% | +0.6 pts |
| Federated learning and privacy | 29 | 2.0% | +0.2 pts |
| 3D vision | 24 | 1.7% | +0.2 pts |
| Large language models | 22 | 1.5% | +0.6 pts |
| Vision-language and multimodal | 20 | 1.4% | -0.2 pts |
| Time series | 20 | 1.4% | steady |
| Video | 15 | 1.0% | -0.4 pts |
| Continual learning | 13 | 0.9% | +0.3 pts |
| Point clouds | 10 | 0.7% | +0.2 pts |
Fastest-growing topics at NeurIPS 2019
Change in share of NeurIPS papers from 2018 to 2019, topics with at least 10 papers.
- GNN architectures (Graph learning): 5 → 19 papers
- Multi-armed bandits (Bandits and online learning): 10 → 25 papers
- Graph algorithms and clustering (Graph learning): 16 → 33 papers
- Implicit bias and generalization (Optimization): 21 → 39 papers
- Neural architecture search (Architectures and efficiency): 2 → 12 papers
- RL theory and MDPs (Bandits and online learning): 2 → 11 papers
- Human and embodied modeling (Vision-language and multimodal): 3 → 11 papers
- Graph self-supervised learning (Graph learning): 5 → 13 papers
- Human-AI and goal-conditioned (Multi-agent systems and games): 6 → 14 papers
- Online and replay-based (Continual learning): 4 → 11 papers
More venues
Same year: ICML 2019 · ICLR 2019 · CVPR 2019 · AAAI 2019 · ICCV 2019 · TPAMI 2019 · IJCV 2019 · JMLR 2019
NeurIPS in other years: 2016 · 2017 · 2018 · 2020 · 2021 · 2022 · 2023 · 2024 · 2025 · 2026
