Active Deep Learning on Entity Resolution by Risk Sampling
arXiv:2012.12960
Abstract
While the state-of-the-art performance on entity resolution (ER) has been achieved by deep learning, its effectiveness depends on large quantities of accurately labeled training data. To alleviate the data labeling burden, Active Learning (AL) presents itself as a feasible solution that focuses on data deemed useful for model training. Building upon the recent advances in risk analysis for ER, which can provide a more refined estimate on label misprediction risk than the simpler classifier outputs, we propose a novel AL approach of risk sampling for ER. Risk sampling leverages misprediction risk estimation for active instance selection. Based on the core-set characterization for AL, we theoretically derive an optimization model which aims to minimize core-set loss with non-uniform Lipschitz continuity. Since the defined weighted K-medoids problem is NP-hard, we then present an efficient heuristic algorithm. Finally, we empirically verify the efficacy of the proposed approach on real data by a comparative study. Our extensive experiments have shown that it outperforms the existing alternatives by considerable margins. Using ER as a test case, we demonstrate that risk sampling is a promising approach potentially applicable to other challenging classification tasks.
arXiv comment13 pages, 6 figures
References in corpus (9)
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- Bayesian Active Learning for Classification and Preference Learning
- Adversarial Active Learning for Deep Networks: a Margin Based Approach
- A Benchmark and Comparison of Active Learning for Logistic Regression
- Discriminative Active Learning
- Stable Recurrent Models
- Active Learning for Speech Recognition: the Power of Gradients
- Bayesian Generative Active Deep Learning
- Low-resource Deep Entity Resolution with Transfer and Active Learning