# Active Deep Learning on Entity Resolution by Risk Sampling

arXiv: https://arxiv.org/abs/2012.12960 · HTML: https://mlsanity.com/paper/2012.12960/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2020.

## Built on by (most cited first, 6 of 6)

- [Deep Active Alignment of Knowledge Graph Entities and Schemata](https://mlsanity.com/paper/2304.04389/) (2023)
- [Cost-Efficient Prompt Engineering for Unsupervised Entity Resolution](https://mlsanity.com/paper/2310.06174/) (2023)
- [Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making](https://mlsanity.com/paper/2106.04174/) (2021)
- [MultiEM: Efficient and Effective Unsupervised Multi-Table Entity Matching](https://mlsanity.com/paper/2308.01927/) (2023)
- [Nearest Neighbor Classifier with Margin Penalty for Active Learning](https://mlsanity.com/paper/2203.09174/) (2022)
- [Adaptive Deep Learning for Breast Cancer Subtype Prediction Via Misprediction Risk Analysis](https://mlsanity.com/paper/2503.12778/) (2025)

## Abstract (arXiv)

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.