Adversarial Label Learning
This addresses the challenge of label scarcity in machine learning for practitioners, though it is incremental as it builds on existing weakly supervised techniques.
The paper tackles the problem of training classifiers without labels by proposing adversarial label learning, which minimizes an upper bound on error rate against an adversary constrained by weak supervision, and experiments on three real datasets show it outperforms other weakly supervised methods.
We consider the task of training classifiers without labels. We propose a weakly supervised method---adversarial label learning---that trains classifiers to perform well against an adversary that chooses labels for training data. The weak supervision constrains what labels the adversary can choose. The method therefore minimizes an upper bound of the classifier's error rate using projected primal-dual subgradient descent. Minimizing this bound protects against bias and dependencies in the weak supervision. Experiments on three real datasets show that our method can train without labels and outperforms other approaches for weakly supervised learning.