chapter five

5 Advanced Active Learning

 

This chapter covers

  • Understanding different methods for combining Uncertainty Sampling & Diversity Sampling in Active Learning to strategically obtain the optimal samples.
  • Implementing machine learning models that predict which unlabeled items will be incorrectly labeled by the model, to identify the most uncertain items to sample for human annotation.
  • Implementing machine learning models that predict which unlabeled items are the least like the training data, to identify the most representative items to sample for human annotation.
  • Architecting Adaptive Transfer Learning for Representative Sampling and Uncertainty Sampling, to increase the diversity of items sampled in one iteration of Active Learning.

In the last two chapters, you learned how to identify where your model is uncertain (what your model “knows it doesn’t know”), and what is missing from your model (what your model “doesn’t know that it doesn’t know”). In this chapter, you will learn how to combine these into a comprehensive Active Learning strategy.

The use cases in the last two chapters are equally relevant here. For almost any machine learning task, you will want to use both Uncertainty Sampling and Diversity Sampling in combination to sample the optimal items for human review.

5.1       Combining Uncertainty Sampling and Diversity Sampling

5.1.1   Least Confidence Sampling with Clustering-based Sampling

5.1.2   Uncertainty Sampling with Model-based Outliers

5.1.3   Uncertainty Sampling with Model-based Outliers and Clustering

5.1.4   Representative Sampling Cluster-based Sampling

5.1.5   Sampling from the Highest Entropy Cluster

5.1.6   Other Combinations of Active Learning Strategies

5.1.7   Combining Active Learning Scores

5.1.8   Expected Error Reduction Sampling

5.2       Active Transfer Learning for Uncertainty Sampling

5.2.1   Making your model predict its own errors

5.2.2   Implementing Active Transfer Learning

5.2.3   Active Transfer Learning with more layers

5.2.4   The pros and cons of Active Transfer Learning

5.3       Applying Active Transfer Learning to Representative Sampling

5.3.1   Making your model predict what it doesn’t know

5.3.2   Active Transfer Learning for Adaptive Representative Sampling

5.3.3   The pros and cons of Active Transfer Learning for Representative Sampling

5.4       Active Transfer Learning for Adaptive Sampling (ATLAS)

5.4.1   How to make Uncertainty Sampling adaptive by predicting the uncertainty

5.4.2   The pros and cons of ATLAS

5.5       Advanced Active Learning Cheatsheets and Further Reading

5.5.1   Further Reading for Advanced Active Learning

5.5.2   Further Reading for Active Transfer Learning