# EXTRACT: Explainable Transparent Control of Bias in Embeddings

arXiv: https://arxiv.org/abs/2311.00115 · HTML: https://mlsanity.com/paper/2311.00115/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 28 references that are in the map.
- First posted on arXiv 31 Oct 2023.

## Builds on (most cited first, 14 of 14)

- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Bias and Debias in Recommender System: A Survey and Future Directions](https://mlsanity.com/paper/2010.03240/) (2020)
- [Censoring Representations with an Adversary](https://mlsanity.com/paper/1511.05897/) (2015)
- [Compositional Fairness Constraints for Graph Embeddings](https://mlsanity.com/paper/1905.10674/) (2019)
- [Barack's Wife Hillary: Using Knowledge-Graphs for Fact-Aware Language Modeling](https://mlsanity.com/paper/1906.07241/) (2019)
- [Commonsense for Generative Multi-Hop Question Answering Tasks](https://mlsanity.com/paper/1809.06309/) (2018)
- [CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Bases](https://mlsanity.com/paper/1606.01994/) (2016)
- [Biased Embeddings from Wild Data: Measuring, Understanding and Removing](https://mlsanity.com/paper/1806.06301/) (2018)
- [Exploring Scholarly Data by Semantic Query on Knowledge Graph Embedding Space](https://mlsanity.com/paper/1909.08191/) (2019)

## Built on by (most cited first, 2 of 2)

- [Quantifying Compositionality of Classic and State-of-the-Art Embeddings](https://mlsanity.com/paper/2509.19332/) (2025)
- [Compositional Fusion of Signals in Data Embedding](https://mlsanity.com/paper/2311.11085/) (2023)

## Abstract (arXiv)

Knowledge Graphs are a widely used method to represent relations between entities in various AI applications, and Graph Embedding has rapidly become a standard technique to represent Knowledge Graphs in such a way as to facilitate inferences and decisions. As this representation is obtained from behavioural data, and is not in a form readable by humans, there is a concern that it might incorporate unintended information that could lead to biases. We propose EXTRACT: a suite of Explainable and Transparent methods to ConTrol bias in knowledge graph embeddings, so as to assess and decrease the implicit presence of protected information. Our method uses Canonical Correlation Analysis (CCA) to investigate the presence, extent and origins of information leaks during training, then decomposes embeddings into a sum of their private attributes by solving a linear system. Our experiments, performed on the MovieLens1M dataset, show that a range of personal attributes can be inferred from a user's viewing behaviour and preferences, including gender, age, and occupation. Further experiments, performed on the KG20C citation dataset, show that the information about the conference in which a paper was published can be inferred from the citation network of that article. We propose four transparent methods to maintain the capability of the embedding to make the intended predictions without retaining unwanted information. A trade-off between these two goals is observed.