tensorflow / tensorflow/privacy

Poor performance while using DPAdam in WGAN-GP

Open
#112 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2k
Forks
477
Avg merge
22h 12m
Merged PRs (30d)
1

Description

I am trying to add privacy to my WGAN. With Adam optimizer without DP, my WGAN works well. But after I change it to

optimizer = DPAdamGaussianOptimizer(
l2_norm_clip=3,
noise_multiplier=0.5,
num_microbatches=1,
learning_rate=0.001)

The D_loss never went smaller than 1. And my output is not convincing neither. Anybody knows how to fix it?

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No files or tests are named. Start by reproducing the WGAN-GP training behavior with the shown DPAdamGaussianOptimizer settings, then compare it with the non-DP Adam configuration. Check whether the loss and output differences are reproducible and document a confirmed cause or a minimal, validated fix.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, tensorflow
Domain
machine-learning, security
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.