Unsupervised or Indirectly Supervised Learning
PacGAN: The power of two samples in generative adversarial networks
Zinan Lin, Ashish Khetan, Giulia Fanti, Sewoong Oh
Neural Information Processing Systems http://nips.cc/
MarginGAN: Adversarial Training in Semi-Supervised Learning
The newfeature isthattheclassifier attempts toincrease themarginofrealexamples and to decrease the margin of fake examples.
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/
Graph Agreement Models for Semi-Supervised Learning
Otilia Stretcu, Krishnamurthy Viswanathan, Dana Movshovitz-Attias, Emmanouil Platanios, Sujith Ravi, Andrew Tomkins
Neural Information Processing Systems http://nips.cc/
Debiased Self-Training for Semi-Supervised Learning
Despite its popularity, self-training is well-believed to be unreliable and often leads to training instability.
