README.md

May 8, 2025 ยท View on GitHub

Probabilistic Group Mask Guided Discrete Optimization for Incremental Learning-ICML2025

This is the official implementation of PGM in the paper in Pytorch.

Dependency

Dataset

  • CIFAR-100 Split (available current version)
  • CIFAR-100 Superclass (available current version)
  • TinyImageNet (available current version)

Installation

To execute the codes for running experiments, run the following.

pip install -r requirements.txt

Training

We provide several training examples with this repositories:

  • To train PGM on Cifar100 on GPU [GPU_ID] with seed number [SEED] , simply run the following
>> ./scripts/pgm_cifar100.sh [GPU_ID] [SEED]