Active Learning

298 papers with code • 0 benchmarks • 13 datasets

Active Learning is a paradigm in supervised machine learning which uses fewer training examples to achieve better optimization by iteratively training a predictor, and using the predictor in each iteration to choose the training examples which will increase its chances of finding better configurations and at the same time improving the accuracy of the prediction model

Source: Polystore++: Accelerated Polystore System for Heterogeneous Workloads

Greatest papers with code

modAL: A modular active learning framework for Python

modAL-python/modAL 2 May 2018

modAL is a modular active learning framework for Python, aimed to make active learning research and practice simpler.

Active Learning

Sampling Bias in Deep Active Classification: An Empirical Study

Xtra-Computing/thundersvm IJCNLP 2019

The exploding cost and time needed for data labeling and model training are bottlenecks for training DNN models on large datasets.

Active Learning General Classification +1

Active Anomaly Detection via Ensembles: Insights, Algorithms, and Interpretability

shubhomoydas/ad_examples 23 Jan 2019

In this paper, we study the problem of active learning to automatically tune ensemble of anomaly detectors to maximize the number of true anomalies discovered.

Active Learning Anomaly Detection

Active Anomaly Detection via Ensembles

shubhomoydas/ad_examples 17 Sep 2018

First, we present an important insight into how anomaly detector ensembles are naturally suited for active learning.

Active Learning Anomaly Detection

libact: Pool-based Active Learning in Python

ntucllab/libact 1 Oct 2017

libact is a Python package designed to make active learning easier for general users.

Active Learning

ALiPy: Active Learning in Python

NUAA-AL/ALiPy 12 Jan 2019

Supervised machine learning methods usually require a large set of labeled examples for model training.

Active Learning

Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes

google-research/meta-dataset NeurIPS 2019

We introduce a conditional neural process based approach to the multi-task classification setting for this purpose, and establish connections to the meta-learning and few-shot learning literature.

Active Learning Continual Learning +3

Active Learning for Interactive Neural Machine Translation of Data Streams

lvapeab/nmt-keras CONLL 2018

We study the application of active learning techniques to the translation of unbounded data streams via interactive neural machine translation.

Active Learning Machine Translation

DEUP: Direct Epistemic Uncertainty Prediction

google/uncertainty-baselines 16 Feb 2021

Epistemic uncertainty is the part of out-of-sample prediction error due to the lack of knowledge of the learner.

Active Learning

Self-Regulated Interactive Sequence-to-Sequence Learning

joeynmt/joeynmt ACL 2019

Not all types of supervision signals are created equal: Different types of feedback have different costs and effects on learning.

Active Learning Machine Translation