label proportion
PAC Learning Linear Thresholds from Label Proportions
The goal is to train a good instance classifier.
Country:
- Asia > India (0.04)
- North America > United States (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- Europe > France > Île-de-France > Paris > Paris (0.04)
Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Computational Learning Theory (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning (0.92)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (0.69)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Directed Networks > Bayesian Learning (0.67)
Auditing Privacy Mechanisms via Label Inference Attacks
We propose reconstruction advantage measures to audit label privatization mechanisms.
Country:
- North America > United States > California > San Francisco County > San Francisco (0.14)
- North America > United States > Hawaii > Honolulu County > Honolulu (0.04)
- North America > United States > California > Santa Clara County > San Jose (0.04)
- (2 more...)
Technology:
A Unified Approach to Count-Based Weakly-Supervised Learning
High-quality labels are often very scarce, whereas unlabeled data with inferred weak labels occurs more naturally.
Country:
- North America > United States > California > Los Angeles County > Los Angeles (0.14)
- North America > Canada > Ontario > Toronto (0.14)
- Oceania > Australia > New South Wales > Sydney (0.04)
- (2 more...)
Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Inductive Learning (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Uncertainty (0.68)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.46)
Learning from Label Proportions with Generative Adversarial Networks
Jiabin Liu, Bo Wang, Zhiquan Qi, YingJie Tian, Yong Shi
Neural Information Processing Systems http://nips.cc/
Country:
- Asia > China > Beijing > Beijing (0.05)
- North America > United States > Texas (0.04)
- North America > Canada (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Unsupervised or Indirectly Supervised Learning (0.31)
Country:
- North America > United States > Michigan > Washtenaw County > Ann Arbor (0.14)
- North America > Canada (0.04)
- Europe > France > Hauts-de-France > Nord > Lille (0.04)
- Asia > Middle East > Jordan (0.04)
Technology:
Country:
- North America > United States > Michigan > Washtenaw County > Ann Arbor (0.14)
- North America > Canada (0.04)
- Europe > France > Hauts-de-France > Nord > Lille (0.04)
Industry:
Technology:
- Information Technology > Artificial Intelligence > Representation & Reasoning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (0.93)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Directed Networks > Bayesian Learning (0.93)
- Information Technology > Data Science > Data Mining (0.68)
Easy Learning from Label Proportions
Albeit, the objective of the learner is to achieve low task loss at an individual instance level.
Technology:
Country:
- North America > United States > Massachusetts > Middlesex County > Cambridge (0.04)
- Asia > India (0.04)
Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (0.70)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Directed Networks > Bayesian Learning (0.67)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (0.46)