FAIRER: Fairness as Decision Rationale Alignment
Jul 24, 2023
Speakers
Li Tianlin
Speaker · 0 followers
Aishan Liu
Speaker · 0 followers
Mengnan Du
Speaker · 0 followers
Zhiming Li
Speaker · 0 followers
About
Deep neural networks (DNNs) have achieved remarkable accuracy, but they often suffer from fairness issues, as deep models typically show distinct accuracy differences among some specific subgroups (e.g., males and females). Existing research addresses this critical issue by employing fairness-aware loss functions to constrain the last-layer outputs and directly regularize DNNs. Although the fairness of DNNs is improved, it is unclear how the trained network makes a fair prediction, which limits future fairness improvements. In this paper, we investigate fairness from the perspective of decision rationale and define the neuron parity score to characterize the fair decision process of networks by analyzing neuron behaviors in various subgroups. Extensive empirical studies show that the unfair issue could arise from the unaligned decision rationales of subgroups. Existing fairness regularization terms fail to achieve decision rationale alignment because they only constrain last-layer outputs while ignoring intermediate neuron alignment. To address the issue, we formulate the fairness as a new task, i.e., decision rationale alignment that requires DNNs’ neurons to have consistent responses on subgroups at both intermediate processes and the final prediction. To make this idea practical during optimization, we relax the naive objective function and propose gradient-guided parity alignment, which encourages gradient-weighted consistency of neurons across subgroups. Extensive experiments on a variety of datasets show that our method can improve fairness while maintaining high accuracy and outperforming other baselines by a large margin. We have released our codes at https://anonymous.4open.science/r/fairer_submission-F176/.Deep neural networks (DNNs) have achieved remarkable accuracy, but they often suffer from fairness issues, as deep models typically show distinct accuracy differences among some specific subgroups (e.g., males and females). Existing research addresses this critical issue by employing fairness-aware loss functions to constrain the last-layer outputs and directly regularize DNNs. Although the fairness of DNNs is improved, it is unclear how the trained network makes a fair prediction, which limits…
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Dropout Reduces Underfitting
Watch later
Zhuang Liu, …
Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs
Watch later
Saro Passaro, …
Near-Minimax-Optimal Risk-Sensitive RL with CVaR
Watch later
Kaiwen Wang, …
Randomized Gaussian Process Upper Confidence Bound with Tight Bayesian Regret Bounds
Watch later
Shion Takeno, …
Calibrating Multimodal Learning
Watch later
Huan Ma, …
