Configure Components

The configs for experiment and evaluation pipelines in CLArena are divided into components. They include:

Component	Description
CL Dataset	Continual learning dataset
MTL Dataset	Multi-task learning dataset
STL Dataset	Single-task learning dataset
CL Algorithm	Continual learning algorithm
CUL Algorithm	Continual unlearning algorithm
MTL Algorithm	Multi-task learning algorithm
STL Algorithm	Single-task learning algorithm
Backbone Network	The backbone neural network architecture
Optimizer	The optimization algorithm used for training
Learning Rate Scheduler	The learning rate scheduling strategy
Trainer	The training configuration using PyTorch Lightning Trainer
Metrics	The evaluation metrics used to assess model performance
Lightning Loggers	PyTorch Lightning Logger settings
Callbacks	The callbacks (additional operation hooks) used during training and evaluation
Other Configs	Config categories not covered above