A Meta-Learning Approach to One-Step Active-Learning

We consider the problem of learning when obtaining the training labels is costly, which is usually tackled in the literature using active-learning techniques. These approaches provide strategies to choose the examples to label before or during training. These strategies are usually based on heuristics or even theoretical measures, but are not learned as they are directly used during training. We design a model which aims at \textit{learning active-learning strategies} using a meta-learning setting. More specifically, we consider a pool-based setting, where the system observes all the examples of the dataset of a problem and has to choose the subset of examples to label in a single shot. Experiments show encouraging results.

[1]  Dale Schuurmans,et al.  Discriminative Batch Mode Active Learning , 2007, NIPS.

[2]  Mark Craven,et al.  Multiple-Instance Active Learning , 2007, NIPS.

[3]  Chris H. Q. Ding,et al.  Selective Labeling via Error Bound Minimization , 2012, NIPS.

[4]  Oriol Vinyals,et al.  Matching Networks for One Shot Learning , 2016, NIPS.

[5]  Tong Zhang,et al.  The Value of Unlabeled Data for Classification Problems , 2000, ICML 2000.

[6]  Burr Settles,et al.  Active Learning Literature Survey , 2009 .

[7]  Daan Wierstra,et al.  Meta-Learning with Memory-Augmented Neural Networks , 2016, ICML.

[8]  Andrew McCallum,et al.  Toward Optimal Active Learning through Monte Carlo Estimation of Error Reduction , 2001, ICML 2001.

[9]  Jinbo Bi,et al.  Active learning via transductive experimental design , 2006, ICML.

[10]  Shlomo Argamon,et al.  Committee-Based Sampling For Training Probabilistic Classi(cid:12)ers , 1995 .

[11]  Chelsea Finn,et al.  Active One-shot Learning , 2017, ArXiv.

[12]  Samy Bengio,et al.  Order Matters: Sequence to sequence for sets , 2015, ICLR.

[13]  David A. Cohn,et al.  Improving generalization with active learning , 1994, Machine Learning.

[14]  Philip Bachman,et al.  Learning Algorithms for Active Learning , 2017, ICML.

[15]  Jeff A. Bilmes,et al.  Label Selection on Graphs , 2009, NIPS.

[16]  Raymond J. Mooney,et al.  Diverse ensembles for active learning , 2004, ICML.

[17]  Gerald J. Sussman,et al.  Sparse Representations for Fast, One-Shot Learning , 1997, AAAI/IAAI.