Supplementary codes for the submission "An Investigation of Representation and Allocation Harms in Contrastive Learning"
Our case-study of controlled underrepresentation on CIFAR10 dataset [1] are implemented with three contrastive learning protocol: (1) SimCLR [2], (2) SimSIAM [3], and (3) boosted contrastive learning (BCL) with SimCLR protocol [4].
[1] Krizhevsky, A., & Hinton, G. (2009). Learning multiple layers of features from tiny images.
[2] Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020, November). A simple framework for contrastive learning of visual representations. In International conference on machine learning (pp. 1597-1607). PMLR.
[3] Chen, X., & He, K. (2021). Exploring simple siamese representation learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 15750-15758).
[4] Zhou, Z., Yao, J., Wang, Y. F., Han, B., & Zhang, Y. (2022, June). Contrastive learning with boosted memorization. In International Conference on Machine Learning (pp. 27367-27377). PMLR.