NeurIPS 2016 accepted papers on Label-efficient and robust learning
36 of the 570 papers accepted at NeurIPS 2016 (6.3%) are on Label-efficient and robust learning. They fall into 6 topics.
See NeurIPS 2016 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
Recognition and long-tail · 22 papers
- Equality of Opportunity in Supervised Learning (2,184 citations)
- Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings (1,340 citations)
- Improved Deep Metric Learning with Multi-class N-pair Loss Objective (1,329 citations)
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets (1,227 citations)
- Dual Learning for Machine Translation (720 citations)
- Examples are not enough, learn to criticize! Criticism for Interpretability (525 citations)
- Local Similarity-Aware Deep Feature Embedding (116 citations)
- DeepMath - Deep Sequence Models for Premise Selection (112 citations)
- Supervised Word Mover's Distance (98 citations)
- Deep Neural Networks with Inexact Matching for Person Re-Identification (96 citations)
- CliqueCNN: Deep Unsupervised Exemplar Learning (90 citations)
- Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning (80 citations)
and 10 more in the interactive map.
Domain adaptation and generalization · 4 papers
- Domain Separation Networks (1,102 citations)
- Learning Transferrable Representations for Unsupervised Domain Adaptation (261 citations)
- Hypothesis Testing in Unsupervised Domain Adaptation with Applications in Alzheimer's Disease (17 citations)
- Unsupervised Domain Adaptation with Residual Transfer Networks
Semi-supervised learning · 4 papers
Noisy labels · 3 papers
Zero-/few-shot and meta-learning · 2 papers
Self-supervised and contrastive · 1 paper
- Learning Bound for Parameter Transfer Learning (6 citations)
