ErGAN: Generative Adversarial Networks for Entity Resolution
This work is significant for researchers and practitioners in data integration and data quality, as it offers a more efficient way to train entity resolution models by reducing the reliance on costly human labeling.
This paper addresses the high labeling cost in learning-based entity resolution by proposing ErGAN, a generative adversarial network. ErGAN significantly reduces the need for human-labeled data and outperforms existing state-of-the-art unsupervised, semi-supervised, and supervised methods.
Entity resolution targets at identifying records that represent the same real-world entity from one or more datasets. A major challenge in learning-based entity resolution is how to reduce the label cost for training. Due to the quadratic nature of record pair comparison, labeling is a costly task that often requires a significant effort from human experts. Inspired by recent advances of generative adversarial network (GAN), we propose a novel deep learning method, called ErGAN, to address the challenge. ErGAN consists of two key components: a label generator and a discriminator which are optimized alternatively through adversarial learning. To alleviate the issues of overfitting and highly imbalanced distribution, we design two novel modules for diversity and propagation, which can greatly improve the model generalization power. We have conducted extensive experiments to empirically verify the labeling and learning efficiency of ErGAN. The experimental results show that ErGAN beats the state-of-the-art baselines, including unsupervised, semi-supervised, and unsupervised learning methods.