unlabeled data
Unlabeled data refers to data points that do not have associated output labels. In unsupervised and semi-supervised learning, such data is utilized to infer structure or patterns without explicit mappings to target outputs.
- Attention-based clustering
- Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery
- Evaluating multiple models using labeled and unlabeled data
- No Experts, No Problem: Avoidance Learning from Bad Demonstrations
- OmniGaze: Reward-inspired Generalizable Gaze Estimation in the Wild
- On the sample complexity of semi-supervised multi-objective learning
- Optimal Mistake Bounds for Transductive Online Learning
- Optimal Mistake Bounds for Transductive Online Learning
- Prediction-Powered Semi-Supervised Learning with Online Power Tuning
- Revisiting Semi-Supervised Learning in the Era of Foundation Models
- TTRL: Test-Time Reinforcement Learning
- Theoretical Insights into In-context Learning with Unlabeled Data
- Uncertain Knowledge Graph Completion via Semi-Supervised Confidence Distribution Learning
- Unlabeled Data Can Provably Enhance In-Context Learning of Transformers
- Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs