SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.03935 · ICML · 2023

Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks

Huaxiu Yao, James Zou, Kenji Kawaguchi, Zhun Deng, Ting Ye, Yuzhen Mao

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 14 functions out of this paper's own repositories and ran 13 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
modar7/the_fairness_stitch pwc_unofficial 13 of 14
FunctionStatusWhere it lives
accuracy_equality_difference Ran modar7/the_fairness_stitch/src/metrics.py
code served (permissive licence) · get_code("b113af2bdb4b7ad0")
ae_constraint Ran modar7/the_fairness_stitch/src/fairness_constraints.py
code served (permissive licence) · get_code("3e2bcc37f0d29b39")
compute_auc Ran modar7/the_fairness_stitch/src/utils_abroca.py
code served (permissive licence) · get_code("f34aff34be2461e9")
compute_roc Ran modar7/the_fairness_stitch/src/utils_abroca.py
code served (permissive licence) · get_code("5bf52700b6ec83bf")
eo_constraint Ran modar7/the_fairness_stitch/src/fairness_constraints.py
code served (permissive licence) · get_code("d1f364aa232405ad")
get_pred Ran modar7/the_fairness_stitch/src/utils.py
code served (permissive licence) · get_code("c691b280c17d59c0")
get_pred_Stitched_Model Ran modar7/the_fairness_stitch/src/utils.py
code served (permissive licence) · get_code("0f0267a4b0a6ffd7")
interpolate_roc_fun Ran modar7/the_fairness_stitch/src/utils_abroca.py
code served (permissive licence) · get_code("833b23ea24be2333")
max_min_fairness Ran modar7/the_fairness_stitch/src/metrics.py
code served (permissive licence) · get_code("33a0eb0cb76eac7a")
mmf_constraint Ran modar7/the_fairness_stitch/src/fairness_constraints.py
code served (permissive licence) · get_code("1fda7cb005b7308f")
prepare_data Ran modar7/the_fairness_stitch/src/data_processing.py
code served (permissive licence) · get_code("c700a303a2482780")
print_acc_auc_stats Ran modar7/the_fairness_stitch/src/utils.py
code served (permissive licence) · get_code("3016678b713de42a")
valid_per_epoch Ran modar7/the_fairness_stitch/src/FDR.py
code served (permissive licence) · get_code("69501a60076aa16a")
compute_abroca Not yet run modar7/the_fairness_stitch/src/compute_abroca.py
code served (permissive licence) · get_code("77748e5ebfbb1e32")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

As machine learning has been deployed ubiquitously across applications in modern data science, algorithmic fairness has become a great concern. Among them, imposing fairness constraints during learning, i.e. in-processing fair training, has been a popular type of training method because they don't require accessing sensitive attributes during test time in contrast to post-processing methods. While this has been extensively studied in classical machine learning models, their impact on deep neural networks remains unclear. Recent research has shown that adding fairness constraints to the objective function leads to severe over-fitting to fairness criteria in large models, and how to solve this challenge is an important open question. To tackle this, we leverage the wisdom and power of pre-training and fine-tuning and develop a simple but novel framework to train fair neural networks in an efficient and inexpensive way -lastlayer fine-tuning alone can effectively promote fairness in deep neural networks. This framework offers valuable insights into representation learning for training fair neural networks. The code is published at https://github.com/ yuzhenmao/Fairness-Finetuning

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2304.03935")
get_code_for_paper("2304.03935")
have("2304.03935")

Connect an agent — have() is free.