# Record fusion: A learning approach

arXiv: https://arxiv.org/abs/2006.10208 · HTML: https://mlsanity.com/paper/2006.10208/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2020.

## Built on by (most cited first, 3 of 3)

- [Saga: A Platform for Continuous Construction and Serving of Knowledge At Scale](https://mlsanity.com/paper/2204.07309/) (2022)
- [Uncertainty Management in the Construction of Knowledge Graphs: a Survey](https://mlsanity.com/paper/2405.16929/) (2024)
- [Sig2Model: A Boosting-Driven Model for Updatable Learned Indexes](https://mlsanity.com/paper/2509.20781/) (2025)

## Abstract (arXiv)

Record fusion is the task of aggregating multiple records that correspond to the same real-world entity in a database. We can view record fusion as a machine learning problem where the goal is to predict the "correct" value for each attribute for each entity. Given a database, we use a combination of attribute-level, recordlevel, and database-level signals to construct a feature vector for each cell (or (row, col)) of that database. We use this feature vector alongwith the ground-truth information to learn a classifier for each of the attributes of the database. Our learning algorithm uses a novel stagewise additive model. At each stage, we construct a new feature vector by combining a part of the original feature vector with features computed by the predictions from the previous stage. We then learn a softmax classifier over the new feature space. This greedy stagewise approach can be viewed as a deep model where at each stage, we are adding more complicated non-linear transformations of the original feature vector. We show that our approach fuses records with an average precision of ~98% when source information of records is available, and ~94% without source information across a diverse array of real-world datasets. We compare our approach to a comprehensive collection of data fusion and entity consolidation methods considered in the literature. We show that our approach can achieve an average precision improvement of ~20%/~45% with/without source information respectively.