INO-SGD down-weights data in each batch to improve model performance on strongly private data while satisfying individualized differential privacy constraints.
Thai and Linh Thi Xuan Phan NhatHai Phan , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces a multitask adversarial model that learns representations hiding sensitive attributes while preserving task information to balance fairness, privacy, and accuracy with minimal performance loss.
citing papers explorer
-
INO-SGD: Addressing Utility Imbalance under Individualized Differential Privacy
INO-SGD down-weights data in each batch to improve model performance on strongly private data while satisfying individualized differential privacy constraints.
-
Balancing Fairness, Privacy, and Accuracy: A Multitask Adversarial Framework for Centralized Data-Driven Systems
Introduces a multitask adversarial model that learns representations hiding sensitive attributes while preserving task information to balance fairness, privacy, and accuracy with minimal performance loss.