# CAFIN: Centrality Aware Fairness inducing IN-processing for Unsupervised Representation Learning on Graphs

arXiv: https://arxiv.org/abs/2304.04391 · HTML: https://mlsanity.com/paper/2304.04391/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 45 references that are in the map.
- First posted on arXiv 10 Apr 2023.

## Builds on (most cited first, 21 of 21)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Multi-scale Attributed Node Embedding](https://mlsanity.com/paper/1909.13021/) (2019)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Metrics for Multi-Class Classification: an Overview](https://mlsanity.com/paper/2008.05756/) (2020)
- [Predicting multicellular function through multi-layer tissue networks](https://mlsanity.com/paper/1707.04638/) (2017)
- [Towards Unsupervised Deep Graph Structure Learning](https://mlsanity.com/paper/2201.06367/) (2022)
- [Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns](https://mlsanity.com/paper/2106.06586/) (2021)
- [FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning](https://mlsanity.com/paper/2104.14210/) (2021)
- [E-GraphSAGE: A Graph Neural Network based Intrusion Detection System for IoT](https://mlsanity.com/paper/2103.16329/) (2021)
- [On Generalized Degree Fairness in Graph Neural Networks](https://mlsanity.com/paper/2302.03881/) (2023)
- [RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Network](https://mlsanity.com/paper/2202.13547/) (2022)
- [A Survey on Fairness for Machine Learning on Graphs](https://mlsanity.com/paper/2205.05396/) (2022)
- [Adversarial Graph Embeddings for Fair Influence Maximization over Social Networks](https://mlsanity.com/paper/2005.04074/) (2020)
- [The Effects of Randomness on the Stability of Node Embeddings](https://mlsanity.com/paper/2005.10039/) (2020)
- [InfoFair: Information-Theoretic Intersectional Fairness](https://mlsanity.com/paper/2105.11069/) (2021)
- [Gaps in Information Access in Social Networks](https://mlsanity.com/paper/1903.02047/) (2019)

## Built on by (most cited first, 1 of 1)

- [A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks](https://mlsanity.com/paper/2412.00789/) (2024)

## Abstract (arXiv)

Unsupervised Representation Learning on graphs is gaining traction due to the increasing abundance of unlabelled network data and the compactness, richness, and usefulness of the representations generated. In this context, the need to consider fairness and bias constraints while generating the representations has been well-motivated and studied to some extent in prior works. One major limitation of most of the prior works in this setting is that they do not aim to address the bias generated due to connectivity patterns in the graphs, such as varied node centrality, which leads to a disproportionate performance across nodes. In our work, we aim to address this issue of mitigating bias due to inherent graph structure in an unsupervised setting. To this end, we propose CAFIN, a centrality-aware fairness-inducing framework that leverages the structural information of graphs to tune the representations generated by existing frameworks. We deploy it on GraphSAGE (a popular framework in this domain) and showcase its efficacy on two downstream tasks - Node Classification and Link Prediction. Empirically, CAFIN consistently reduces the performance disparity across popular datasets (varying from 18 to 80% reduction in performance disparity) from various domains while incurring only a minimal cost of fairness.