[Re] Latent Embedding Feedback and Discriminative Featuresfor Zero-Shot Classification (Under Review)

TF-VAEGAN proposes to enforce a semantic embedding decoder (SED) at training, feature synthesis and classification stages of (generalized) zero-shot learning.

[Re] Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation

"Programmer” is more closely associated with “man” and “homemaker” is more closely associated with “woman”. Such gender bias has also been shown to propagate in downstream tasks.