Timezone: »

Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets
Guy Hacohen · Avihu Dekel · Daphna Weinshall

Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #233

Investigating active learning, we focus on the relation between the number of labeled examples (budget size), and suitable querying strategies. Our theoretical analysis shows a behavior reminiscent of phase transition: typical examples are best queried when the budget is low, while unrepresentative examples are best queried when the budget is large. Combined evidence shows that a similar phenomenon occurs in common classification models. Accordingly, we propose TypiClust -- a deep active learning strategy suited for low budgets. In a comparative empirical investigation of supervised learning, using a variety of architectures and image datasets, TypiClust outperforms all other active learning strategies in the low-budget regime. Using TypiClust in the semi-supervised framework, performance gets an even more significant boost. In particular, state-of-the-art semi-supervised methods trained on CIFAR-10 with 10 labeled examples selected by TypiClust, reach 93.2% accuracy -- an improvement of 39.4% over random selection. Code is available at https://github.com/avihu111/TypiClust.

Author Information

Guy Hacohen (Hebrew University of Jerusalem)
Avihu Dekel (Hebrew University)
Avihu Dekel

I’m a CS MSc Student at Daphna Weinshall Lab in the Hebrew University of Jerusalem. My research interests include Active learning, Semi-Supervised learning, Anomaly detection, Unsupervised Learning and many other fields. I’m a TA on Introduction to Machine Learning (67577).

Daphna Weinshall (Hebrew University of Jerusalem, Israel)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors