Timezone: »
Poster
Improved Algorithms for Neural Active Learning
Yikun Ban · Yuheng Zhang · Hanghang Tong · Arindam Banerjee · Jingrui He
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
-
2021 : Machine Learning and Dynamical Models for Sub-seasonal Climate Forecasting »
Sijie He · Xinyan Li · Laurie Trenary · Benjamin Cash · Timothy DelSole · Arindam Banerjee -
2022 Poster: A Deep Learning Dataloader with Shared Data Preparation »
jian xie · Jingwei Xu · Guochang Wang · Yuan Yao · Zenan Li · Chun Cao · Hanghang Tong -
2022 : COIN: Co-Cluster Infomax for Bipartite Graphs »
Baoyu Jing · Yuchen Yan · Yada Zhu · Hanghang Tong -
2022 Poster: CoNSoLe: Convex Neural Symbolic Learning »
Haoran Li · Yang Weng · Hanghang Tong -
2022 Poster: Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative »
Tianxin Wei · Yuning You · Tianlong Chen · Yang Shen · Jingrui He · Zhangyang Wang -
2022 Poster: Distribution-Informed Neural Networks for Domain Adaptation Regression »
Jun Wu · Jingrui He · Sheng Wang · Kaiyu Guan · Elizabeth Ainsworth -
2022 Poster: Deep Active Learning by Leveraging Training Dynamics »
Haonan Wang · Wei Huang · Ziwei Wu · Hanghang Tong · Andrew J Margenot · Jingrui He -
2019 Poster: Robust Principal Component Analysis with Adaptive Neighbors »
Rui Zhang · Hanghang Tong -
2012 Poster: GenDeR: A Generic Diversified Ranking Algorithm »
Jingrui He · Hanghang Tong · Qiaozhu Mei · Boleslaw K Szymanski -
2007 Spotlight: Nearest-Neighbor-Based Active Learning for Rare Category Detection »
Jingrui He · Jaime Carbonell -
2007 Poster: Nearest-Neighbor-Based Active Learning for Rare Category Detection »
Jingrui He · Jaime Carbonell