Adversarial Multiclass Learning under Weak Supervision
with Performance Guarantees
Alessio Mazzetto * 1 Cyrus Cousins * 1 Dylan Sam 1 Stephen H. Bach 1 Eli Upfal 1
Abstract conflict with one another. We assume access to only a
We develop a rigorous approach for using a set small amount of ground-truth labeled data. Much prior
of arbitrarily correlated weak supervision sources work on aggregating noisy labels (Dawid & Skene ...


雷达卡




京公网安备 11010802022788号







