Nevertheless, despite theproliferation ofresearch onalgorithmic fairness inrecent years, veryfew methods exist that can handle multiclass classification tasks with non-binary sensitive attributes.

We use a cyclical embedding to encode these time features discarding the year. We adapted the majority of the baselines using the Time Series Library (TSlib (Wu et al., 2023)), The training of the baselines took place on a single RTX8000 GPU over the course of 100 epochs. During training, a batch size of 64 was consistently employed. Plateau, which gradually decreased the learning rate by a factor of 0.5 after a patience of 10 epochs. For the hyperparameter tuning of the baselines, we employed the Orion package (Bouthillier et al., We report the MAE and RMSE for the easy and difficult splits (presented in the main paper) along with the number of data points for each split.

To better understand the(M,X) D and Assumption 1, let's take a simple example.

Therefore, long-tailed classification is the key to deep learning at scale. However, existing methods are mainly based on reweighting/re-sampling heuristics that lack a fundamental theory. In this paper, weestablish acausal inference framework,which notonlyunravelsthewhysof previous methods, but also derives a new principled solution.

Following the convention of RS, existing methods exploit unique user representation in their model design.