Timezone: »

Improved Algorithms for Neural Active Learning
Yikun Ban · Yuheng Zhang · Hanghang Tong · Arindam Banerjee · Jingrui He

Tue Nov 29 02:00 PM -- 04:00 PM (PST) @ Hall J #938
We improve the theoretical and empirical performance of neural-network(NN)-based active learning algorithms for the non-parametric streaming setting. In particular, we introduce two regret metrics by minimizing the population loss that are more suitable in active learning than the one used in state-of-the-art (SOTA) related work. Then, the proposed algorithm leverages the powerful representation of NNs for both exploitation and exploration, has the query decision-maker tailored for $k$-class classification problems with the performance guarantee, utilizes the full feedback, and updates parameters in a more practical and efficient manner. These careful designs lead to an instance-dependent regret upper bound, roughly improving by a multiplicative factor $O(\log T)$ and removing the curse of input dimensionality. Furthermore, we show that the algorithm can achieve the same performance as the Bayes-optimal classifier in the long run under the hard-margin setting in classification problems. In the end, we use extensive experiments to evaluate the proposed algorithm and SOTA baselines, to show the improved empirical performance.

Author Information

Yikun Ban (University of Illinois at Urbana-Champaign)
Yuheng Zhang (University of Illinois, Urbana Champaign)
Hanghang Tong (University of Illinois at Urbana-Champaign)
Arindam Banerjee (University of Illinois, Urbana Champaign)
Jingrui He (University of Illinois at Urbana-Champaign)

More from the Same Authors