[KongchangAI]
Conceptadversarial debiasing / 对抗性去偏

Adversarial Debiasing

A fairness technique that uses an adversarial training mechanism to suppress a machine learning model from learning systematic biases from demographic features.

Timeline (last 90 days)

Oct 4

The study proposes a multi-objective framework that integrates three technical components: reinforcement learning-based multiple instance learning (RL-MIL), adversarial debiasing, and preference-conditioned hypernetworks.

Unverified50%

All Facts (1)

Unverified

The study proposes a multi-objective framework that integrates three technical components: reinforcement learning-based multiple instance learning (RL-MIL), adversarial debiasing, and preference-conditioned hypernetworks.

50%

Source Articles

Fairness Meets Explainability: The Challenges of a Reinforcement Learning Multi-Instance Student Early Warning SystemOct 4