# Deep Transfer Learning for Multi-source Entity Linkage via Domain Adaptation

arXiv: https://arxiv.org/abs/2110.14509 · HTML: https://mlsanity.com/paper/2110.14509/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 40 references that are in the map.
- First posted on arXiv 27 Oct 2021.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [A Survey of Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1812.02849/) (2018)
- [Deep Entity Matching with Pre-Trained Language Models](https://mlsanity.com/paper/2004.00584/) (2020)
- [DeepER -- Deep Entity Resolution](https://mlsanity.com/paper/1710.00597/) (2017)
- [Low-resource Deep Entity Resolution with Transfer and Active Learning](https://mlsanity.com/paper/1906.08042/) (2019)
- [Modeling Voting for System Combination in Machine Translation](https://mlsanity.com/paper/2007.06943/) (2020)
- [node2bits: Compact Time- and Attribute-aware Node Representations for User Stitching](https://mlsanity.com/paper/1904.08572/) (2019)
- [Reuse and Adaptation for Entity Resolution through Transfer Learning](https://mlsanity.com/paper/1809.11084/) (2018)
- [CorDEL: A Contrastive Deep Learning Approach for Entity Linkage](https://mlsanity.com/paper/2009.07203/) (2020)

## Built on by (most cited first, 7 of 7)

- [Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfer](https://mlsanity.com/paper/2308.09499/) (2023)
- [Generations of Knowledge Graphs: The Crazy Ideas and the Business Impact](https://mlsanity.com/paper/2308.14217/) (2023)
- [Data Cleaning and Machine Learning: A Systematic Literature Review](https://mlsanity.com/paper/2310.01765/) (2023)
- [HumanAL: Calibrating Human Matching Beyond a Single Task](https://mlsanity.com/paper/2205.03209/) (2022)
- [MultiEM: Efficient and Effective Unsupervised Multi-Table Entity Matching](https://mlsanity.com/paper/2308.01927/) (2023)
- [Model Recycling Framework for Multi-Source Data-Free Supervised Transfer Learning](https://mlsanity.com/paper/2508.02039/) (2025)
- [Beyond Scale and Generation: Understanding Language Model-based Entity Matching](https://mlsanity.com/paper/2607.24688/) (2026)

## Abstract (arXiv)

Multi-source entity linkage focuses on integrating knowledge from multiple sources by linking the records that represent the same real world entity. This is critical in high-impact applications such as data cleaning and user stitching. The state-of-the-art entity linkage pipelines mainly depend on supervised learning that requires abundant amounts of training data. However, collecting well-labeled training data becomes expensive when the data from many sources arrives incrementally over time. Moreover, the trained models can easily overfit to specific data sources, and thus fail to generalize to new sources due to significant differences in data and label distributions. To address these challenges, we present AdaMEL, a deep transfer learning framework that learns generic high-level knowledge to perform multi-source entity linkage. AdaMEL models the attribute importance that is used to match entities through an attribute-level self-attention mechanism, and leverages the massive unlabeled data from new data sources through domain adaptation to make it generic and data-source agnostic. In addition, AdaMEL is capable of incorporating an additional set of labeled data to more accurately integrate data sources with different attribute importance. Extensive experiments show that our framework achieves state-of-the-art results with 8.21% improvement on average over methods based on supervised learning. Besides, it is more stable in handling different sets of data sources in less runtime.