An implementation of the state-of-the-art Deep Active Learning algorithms
-
Updated
Sep 19, 2023 - Python
An implementation of the state-of-the-art Deep Active Learning algorithms
[ICLR 2023] Code for our paper "Selective Annotation Makes Language Models Better Few-Shot Learners"
Regression Graph Neural Network (regGNN) for cognitive score prediction.
Code release for ``Towards Discovering the Effectiveness of Moderately Confident Samples for Semi-Supervised Learning'' published in CVPR 2022.
netNorm (network normalization) framework for multi-view network integration (or fusion), recoded up in Python by Ahmed Nebli.
Residual Embedding Similarity-based Network Selection (RESNets) for forecasting network dynamics.
Label-efficiency benchmark — margin sampling hits target accuracy with 38% fewer labels than random, while least-confidence/entropy underperform it. The honest 'which strategy, not whether'
Diversity-aware sample selection and kNN-based extrapolation of a partially measured data layer to the complete dataset.
Active learning and sample selection framework under label budget constraints using uncertainty sampling and small CNN models.
To associate your repository with the sample-selection topic, visit your repo's landing page and select "manage topics."