# A Deep Latent Factor Graph Clustering with Fairness-Utility Trade-off Perspective

arXiv: https://arxiv.org/abs/2510.23507 · HTML: https://mlsanity.com/paper/2510.23507/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 49 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Builds on (most cited first, 28 of 28)

- [Fair Clustering Through Fairlets](https://mlsanity.com/paper/1802.05733/) (2018)
- [Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information](https://mlsanity.com/paper/2009.01454/) (2020)
- [Graph Clustering with Graph Neural Networks](https://mlsanity.com/paper/2006.16904/) (2020)
- [A survey on datasets for fairness-aware machine learning](https://mlsanity.com/paper/2110.00530/) (2021)
- [Neural Collaborative Filtering vs. Matrix Factorization Revisited](https://mlsanity.com/paper/2005.09683/) (2020)
- [Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models](https://mlsanity.com/paper/2005.07959/) (2020)
- [Fairness in Graph Mining: A Survey](https://mlsanity.com/paper/2204.09888/) (2022)
- [Guarantees for Spectral Clustering with Fairness Constraints](https://mlsanity.com/paper/1901.08668/) (2019)
- [Contact patterns in a high school: a comparison between data collected using wearable sensors, contact diaries and friendship surveys](https://mlsanity.com/paper/1506.03645/) (2015)
- [Graph Learning based Recommender Systems: A Review](https://mlsanity.com/paper/2105.06339/) (2021)
- [Fairness-Aware Graph Neural Networks: A Survey](https://mlsanity.com/paper/2307.03929/) (2023)
- [FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization](https://mlsanity.com/paper/2403.12474/) (2024)
- [A Survey of Data-Efficient Graph Learning](https://mlsanity.com/paper/2402.00447/) (2024)
- [Scalable Spectral Clustering with Group Fairness Constraints](https://mlsanity.com/paper/2210.16435/) (2022)
- [Multi-dimensional discrimination in Law and Machine Learning -- A comparative overview](https://mlsanity.com/paper/2302.05995/) (2023)
- [Consistency of Constrained Spectral Clustering under Graph Induced Fair Planted Partitions](https://mlsanity.com/paper/2105.03714/) (2021)
- [Deep matrix factorizations](https://mlsanity.com/paper/2010.00380/) (2020)
- [Rethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical Perspectives](https://mlsanity.com/paper/2110.12141/) (2021)
- [A Scalable Algorithm for Individually Fair K-means Clustering](https://mlsanity.com/paper/2402.06730/) (2024)
- [Verifying Cross-modal Entity Consistency in News using Vision-language Models](https://mlsanity.com/paper/2501.11403/) (2025)
- [Towards Cohesion-Fairness Harmony: Contrastive Regularization in Individual Fair Graph Clustering](https://mlsanity.com/paper/2402.10756/) (2024)
- [Context matters for fairness -- a case study on the effect of spatial distribution shifts](https://mlsanity.com/paper/2206.11436/) (2022)
- [Spectral Normalized-Cut Graph Partitioning with Fairness Constraints](https://mlsanity.com/paper/2307.12065/) (2023)
- [Affinity Clustering Framework for Data Debiasing Using Pairwise Distribution Discrepancy](https://mlsanity.com/paper/2306.01699/) (2023)
- [FairBranch: Mitigating Bias Transfer in Fair Multi-task Learning](https://mlsanity.com/paper/2310.13746/) (2023)
- [Metrics for Community Analysis: A Survey](https://mlsanity.com/paper/1604.03512/) (2016)
- [Self-Paced Multi-Label Learning with Diversity](https://mlsanity.com/paper/1910.03497/) (2019)
- [MMM-fair: An Interactive Toolkit for Exploring and Operationalizing Multi-Fairness Trade-offs](https://mlsanity.com/paper/2509.08156/) (2025)

## Abstract (arXiv)

Fair graph clustering seeks partitions that respect network structure while maintaining proportional representation across sensitive groups, with applications spanning community detection, team formation, resource allocation, and social network analysis. Many existing approaches enforce rigid constraints or rely on multi-stage pipelines (e.g., spectral embedding followed by k-means), limiting trade-off control, interpretability, and scalability. We introduce DFNMF, an end-to-end deep nonnegative tri-factorization tailored to graphs that directly optimizes cluster assignments with a soft statistical-parity regularizer. A single parameter λ tunes the fairness--utility balance, while nonnegativity yields parts-based factors and transparent soft memberships. The optimization uses sparse-friendly alternating updates and scales near-linearly with the number of edges. Across synthetic and real networks, DFNMF achieves substantially higher group balance at comparable modularity, often dominating state-of-the-art baselines on the Pareto front. The code is available at https://github.com/SiamakGhodsi/DFNMF.git.