Fair Generative Modeling via Weak Supervision

Authors: Kristy Choi, Aditya Grover, Trisha Singh, Rui Shu, Stefano Ermon

ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirically, we demonstrate the efficacy of our approach which reduces bias w.r.t. latent factors by an average of up to 34.6% over baselines for comparable image generation using generative adversarial networks.
Researcher Affiliation Academia 1Department of Computer Science, Stanford University 2Department of Statistics, Stanford University.
Pseudocode Yes Algorithm 1 Learning Fair Generative Models
Open Source Code Yes We provide reference implementations in Py Torch (Paszke et al., 2017), and the codebase for this work is open-sourced at https://github.com/ermongroup/fairgen.
Open Datasets Yes We consider the Celeb A (Ziwei Liu & Tang, 2015) dataset, which is commonly used for benchmarking deep generative models and comprises of images of faces with 40 labeled binary attributes.
Dataset Splits Yes For both models, we use a variant of Res Net18 (He et al., 2016) on the standard train and validation splits of Celeb A.
Hardware Specification No For both models, we use a variant of Res Net18 (He et al., 2016) on the standard train and validation splits of Celeb A. For the generative model, we used a Big GAN (Brock et al., 2018) trained to minimize the hinge loss (Lim & Ye, 2017; Tran et al., 2017) objective.
Software Dependencies Yes We provide reference implementations in Py Torch (Paszke et al., 2017)
Experiment Setup Yes Additional details regarding the architectural design and hyperparameters in Supplement C.