The work provides the first formal definitions of Rashomon sets for federated learning and introduces a multiplicity-aware training pipeline evaluated on standard benchmarks.
Bias propagation in federated learning
6 Pith papers cite this work, alongside 3 external citations. Polarity classification is still indexing.
6
Pith papers citing it
3
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
FeDa4Fair is a new library and benchmark for creating federated datasets with heterogeneous client-level biases to standardize evaluation of fairness methods in federated learning.
Empirical audit of LAION-2B-en and LAION-2B-multi finds overrepresentation of young adults, White people, and males plus stereotypical emotion associations across two attribute classifiers.
Derives tractable optimal fair multi-class classifier and supplies in-processing and post-processing algorithms that converge to the accuracy-fairness Pareto frontier.
People apply stricter, more rule-based moral standards to AI systems and their engineers when the AI's human programming is made explicit, while judging the same AI and a human actor similarly when programming is invisible.
Proactive client selection in federated learning via differentially private mutual information and simulated annealing to optimize Potential Federation Loss for utility and fairness.
citing papers explorer
-
Rashomon Sets and Model Multiplicity in Federated Learning
The work provides the first formal definitions of Rashomon sets for federated learning and introduces a multiplicity-aware training pipeline evaluated on standard benchmarks.
-
FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluation
FeDa4Fair is a new library and benchmark for creating federated datasets with heterogeneous client-level biases to standardize evaluation of fairness methods in federated learning.
-
Unmasking LAION-5B: Age, Gender, Race, and Emotion Biases in Large-Scale Image Datasets
Empirical audit of LAION-2B-en and LAION-2B-multi finds overrepresentation of young adults, White people, and males plus stereotypical emotion associations across two attribute classifiers.
-
Demystifying the Optimal Fair Classifier in Multi-Class Classification
Derives tractable optimal fair multi-class classifier and supplies in-processing and post-processing algorithms that converge to the accuracy-fairness Pareto frontier.
-
The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers
People apply stricter, more rule-based moral standards to AI systems and their engineers when the AI's human programming is made explicit, while judging the same AI and a human actor similarly when programming is invisible.
-
Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learning
Proactive client selection in federated learning via differentially private mutual information and simulated annealing to optimize Potential Federation Loss for utility and fairness.