Active learning guided by efficient surrogate learners
- Title
- Active learning guided by efficient surrogate learners
- Authors
- An, Yunpyo; Park, Suyeong; KIM, KWANG IN
- Date Issued
- 2024-02-23
- Publisher
- AAAI Association for the Advancement of Artificial Intelligence
- Abstract
- Re-training a deep learning model each time a single data point receives a new label is impractical due to the inherent complexity of the training process. Consequently, existing active learning (AL) algorithms tend to adopt a batch-based approach where, during each AL iteration, a set of data points is collectively chosen for annotation. However, this strategy frequently leads to redundant sampling, ultimately eroding the efficacy of the labeling procedure. In this paper, we introduce a new AL algorithm that harnesses the power of a Gaussian process surrogate in conjunction with the neural network principal learner. Our proposed model adeptly updates the surrogate learner for every new data instance, enabling it to emulate and capitalize on the continuous learning dynamics of the neural network without necessitating a complete retraining of the principal model for each individual label. Experiments on for benchmark datasets demonstrate that this approach yields significant enhancements, either rivaling or aligning with the performance of state-of-the-art
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/121860
- Article Type
- Conference
- Citation
- Annual AAAI Conference on Artificial Intelligence, 2024-02-23
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.