IALE: Imitating Active Learner Ensembles

by   Christoffer Löffler, et al.

Active learning (AL) prioritizes the labeling of the most informative data samples. As the performance of well-known AL heuristics highly depends on the underlying model and data, recent heuristic-independent approaches that are based on reinforcement learning directly learn a policy that makes use of the labeling history to select the next sample. However, those methods typically need a huge number of samples to sufficiently explore the relevant state space. Imitation learning approaches aim to help out but again rely on a given heuristic. This paper proposes an improved imitation learning scheme that learns a policy for batch-mode pool-based AL. This is similar to previously presented multi-armed bandit approaches but in contrast to them we train a policy that imitates the selection of the best expert heuristic at each stage of the AL cycle directly. We use DAGGER to train the policy on a dataset and later apply it to similar datasets. With multiple AL heuristics as experts, the policy is able to reflect the choices of the best AL heuristics given the current state of the active learning process. We evaluate our method on well-known image datasets and show that we outperform state of the art imitation learners and heuristics.


Active learning for reducing labeling effort in text classification tasks

Labeling data can be an expensive task as it is usually performed manual...

Learning how to Active Learn: A Deep Reinforcement Learning Approach

Active learning aims to select a small subset of data for annotation suc...

Dynamic Ensemble Active Learning: A Non-Stationary Bandit with Expert Advice

Active learning aims to reduce annotation cost by predicting which sampl...

Active Imitation Learning with Noisy Guidance

Imitation learning algorithms provide state-of-the-art results on many s...

Bias-Aware Heapified Policy for Active Learning

The data efficiency of learning-based algorithms is more and more import...

Active Imitation Learning via Reduction to I.I.D. Active Learning

In standard passive imitation learning, the goal is to learn a target po...

Active Learning within Constrained Environments through Imitation of an Expert Questioner

Active learning agents typically employ a query selection algorithm whic...

Please sign up or login with your details

Forgot password? Click here to reset