Good Semi-supervised Learning That Requires a Bad GAN

Zihang Dai, Zhilin Yang, Fan Yang, William W. Cohen, Russ R. Salakhutdinov

Nov-21-2025, 11:15:48 GMT–Neural Information Processing Systems

Theoretically we show that given the discriminator objective, good semi-supervised learning indeed requires a bad generator, and propose the definition of a preferred generator.

artificial intelligence, generator, machine learning, (16 more...)

Neural Information Processing Systems

Nov-21-2025, 11:15:48 GMT

Conferences PDF

Country:
- North America > United States
  - California > Los Angeles County
    - Long Beach (0.04)
  - Pennsylvania > Allegheny County
    - Pittsburgh (0.04)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning
  - Inductive Learning (0.88)
  - Neural Networks > Deep Learning (0.47)
  - Unsupervised or Indirectly Supervised Learning (0.90)

Duplicate Docs Excel Report

Title
Good Semi-supervised Learning That Requires a Bad GAN

Similar Docs Excel Report more

Title	Similarity	Source
None found