CARAML Lab effiCient, fAir, Robust, and Active ML Lab


RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning

Krishnateja Killamsetty December 07, 2021

[Accepted to NeurIPS 2021- Paper, Code] Summary We propose RETRIEVE, a coreset selection framework that selects a subset of unlabeled data by solving a mixed discrete-continuous bi-level optimization problem to efficiently train the models on the selected subset using the existing state-of-the-art semi-supervised algorithms like VAT (Miyato et al., 2019), Mean Teacher (Tarvainen & Valpola, 2017), FixMatch (Sohn et al., 2020). We further empirically demonstrate that using RETRIEVE ena...

SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios

Suraj Kothawade December 07, 2021

[Accepted to NeurIPS 2021- Paper, Code] Over the past several years, active learning (AL) strategies have proven to be useful in reducing labeling costs. However, current methods do not work well when it comes to real-world datasets, which have imperfections and a number of characteristics that make learning from them challenging: Firstly, real-world datasets are imbalanced and some classes are very rare. Some examples of this imbalance come from medical imaging domains; for instance, im...