2021/07/22 by Tam Nguyen, Nguyen, Tam, Raviv Raich +1
Computer Science · #Algorithms and Data Compression #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Text and Document Classification Technologies #cs.LG
paper · pdf · doi:10.48550/arxiv.2107.10804
Machine learning, Multiple instance multiple label learning, Active learning, incomplete label learning
openalex publication_date 2021/07/22 · arxiv created 2021/07/26 · arxiv updated 2021/07/28 · openalex created_date 2021/08/02 · openalex updated_date 2026/07/28
In multiple instance multiple label learning, each sample, a bag, consists of multiple instances. To alleviate labeling complexity, each sample is associated with a set of bag-level labels leaving instances within the bag unlabeled. This setting is more convenient and natural for representing complicated objects, which have multiple semantic meanings. Compared to single instance labeling, this approach allows for labeling larger datasets at an equivalent labeling cost. However, for sufficiently large datasets, labeling all bags may become prohibitively costly. Active learning uses an iterative labeling and retraining approach aiming to provide reasonable classification performance using a small number of labeled samples. To our knowledge, only a few works in the area of active learning in the MIML setting are available. These approaches can provide practical solutions to reduce labeling cost but their efficacy remains unclear. In this paper, we propose a novel bag-class pair based approach for active learning in the MIML setting. Due to the partial availability of bag-level labels, we focus on the incomplete-label MIML setting for the proposed active learning approach. Our approach is based on a discriminative graphical model with efficient and exact inference. For the query process, we adapt active learning criteria to the novel bag-class pair selection strategy. Additionally, we introduce an online stochastic gradient descent algorithm to provide an efficient model update after each query. Numerical experiments on benchmark datasets illustrate the robustness of the proposed approach.