A method that randomly mask out all features coming from a specific time-step in time-series data. If the model used is independent of uneven sequences or missing data in time-series, like attention-based transformers, the masked time-steps can be just ignored in the forward prediction of the model. Otherwise, they have to be masked out with some numerical value.

Dynamic Sparse Training method based on using the gradient norm to select which weights to remove/add in each mask update.

RigL

Rigging the Lottery: Making All Tickets Winners

Temporal Dropout

Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equations

InfoNCE variants demonstrate direct and indirect coupling between the alignment and uniformity terms thus hurting optimisation. The Decoupled Hyperspherical Energy Loss (DHEL) is an NT-Xent variant that completly decouples alignment from uniformity by discarding the corresponding terms from the denominator. In this way optimisation is more efficient and robust to hyper parameter changes.

Source	Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equations
Year
Data Source	Papers with Code archive (CC BY-SA)