The encoder contains three linear layers with output size [d,k,k], each but the last layer is followed by batch normalization, witheps = 0.00005 and momentum=0.1,andtheReLU Thedecoder contains threelinear layers withoutput size [k,k,d] where each but the last layer contains a Batch normlization and the ReLu activation similar asabove. Following the standard linear evaluation procedure inself-supervised learning works (32;34),we used an one linear layer network as the linear decoder for the decoding accuracy. We used the neural activity dataset that is collected from two rhesus macaque monkeys (Chewie and Mihi). They were trained to move the computer cursor to reach a target on a screen.

Fairness-aware machine learning has recently attracted various communities to mitigate discrimination against certain societal groups in data-driven tasks. For fair supervised learning, particularly in pre-processing, there have been two main categories: data fairness and task-tailored fairness. The former directly finds an intermediate distribution among the groups, independent of the type of the downstream model, so a learned downstream classification/regression model returns similar predictive scores to individuals inputting the same covariates irrespective of their sensitive attributes. The latter explicitly takes the supervised learning task into account when constructing the pre-processing map. In this work, we study algorithmic fairness for supervised learning and argue that the data fairness approaches impose overly strong regularization from the perspective of the HGR correlation. This motivates us to devise a novel pre-processing approach tailored to supervised learning. We account for the trade-off between fairness and utility in obtaining the pre-processing map. Then we study the behavior of arbitrary downstream supervised models learned on the transformed data to find sufficient conditions to guarantee their fairness improvement and utility preservation. To our knowledge, no prior work in the branch of task-tailored methods has theoretically investigated downstream guarantees when using pre-processed data. We further evaluate our framework through comparison studies based on tabular and image data sets, showing the superiority of our framework which preserves consistent trade-offs among multiple downstream models compared to recent competing models. Particularly for computer vision data, we see our method alters only necessary semantic features related to the central machine learning task to achieve fairness.