A Survey on Fairness for Machine Learning on Graphs (2022-05-11T00:00:00.000000Z)

TL;DR

This survey is the first one dedicated to fairness for relational data and provides a comprehensive overview of recent contributions in the domain of fair machine learning for graphs, that is classify into pre-processing, in-processing and post-processing models.

Abstract

Nowadays, the analysis of complex phenomena modeled by graphs plays a crucial role in many real-world application domains where decisions can have a strong societal impact. However, numerous studies and papers have recently revealed that machine learning models could lead to potential disparate treatment between individuals and unfair outcomes. In that context, algorithmic contributions for graph mining are not spared by the problem of fairness and present some specific challenges related to the intrinsic nature of graphs: (1) graph data is non-IID, and this assumption may invalidate many existing studies in fair machine learning, (2) suited metric definitions to assess the different types of fairness with relational data and (3) algorithmic challenge on the difficulty of finding a good trade-off between model accuracy and fairness. This survey is the first one dedicated to fairness for relational data. It aims to present a comprehensive review of state-of-the-art techniques in fairness on graph mining and identify the open challenges and future trends. In particular, we start by presenting several sensible application domains and the associated graph mining tasks with a focus on edge prediction and node classification in the sequel. We also recall the different metrics proposed to evaluate potential bias at different levels of the graph mining process; then we provide a comprehensive overview of recent contributions in the domain of fair machine learning for graphs, that we classify into pre-processing, in-processing and post-processing models. We also propose to describe existing graph data, synthetic and real-world benchmarks. Finally, we present in detail five potential promising directions to advance research in studying algorithmic fairness on graphs.

Authors

Manvi Choudhary

1 papers

Charlotte Laclau

1 papers

C. Largeron

1 papers

TL;DR

Abstract

Authors

References101 items

Algorithmic Fairness on Graphs: Methods and Trends

In-Processing Modeling Techniques for Machine Learning Fairness: A Survey

What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective

Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage

Fairness in Graph Mining: A Survey

FairEGM: Fair Link Prediction and Recommendation via Emulated Graph Modification

On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features

Unbiased Graph Embedding with Biased Graph Observations

Fair Graph Mining

A survey on datasets for fairness‐aware machine learning

HM-EIICT: Fairness-aware link prediction in complex networks using community information

Individual Fairness for Graph Neural Networks: A Ranking based Approach

Subgroup Generalization and Fairness of Graph Neural Networks

CrossWalk: Fairness-enhanced Node Representation Learning

FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning

Fairness in rankings and recommendations: an overview

Graph Learning: A Survey

The KL-Divergence between a Graph Model and its Fair I-Projection as a Fairness Regularizer

Towards a Unified Framework for Fair and Stable Graph Representation Learning

Debiasing Knowledge Graph Embeddings

All of the Fairness for Edge Prediction with Optimal Transport

Fairness in Machine Learning: A Survey

Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information

InFoRM: Individual Fairness on Graph Mining

Fair Influence Maximization: A Welfare Optimization Approach

Exploring Algorithmic Fairness in Robust Graph Covering Problems

Achieving Fairness with Decision Trees: An Adversarial Approach

Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models

Adversarial Graph Embeddings for Fair Influence Maximization over Social Networks

Bursting the Filter Bubble: Fairness-Aware Network Link Prediction

DeBayes: a Bayesian method for debiasing network embeddings

The concept of fairness in the GDPR: a linguistic and contextual interpretation

Multi-scale Attributed Node Embedding

MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit

A Survey on Bias and Fairness in Machine Learning

Fairness in Deep Learning: A Computational Perspective

Achieving Causal Fairness through Generative Adversarial Networks

Fairwalk: Towards Fair Graph Embedding

Counterfactual Fairness: Unidentification, Bound and Algorithm

One-Network Adversarial Fairness

Compositional Fairness Constraints for Graph Embeddings

Fairness without Harm: Decoupled Classifiers with Preference Guarantees

Flexibly Fair Representation Learning by Disentanglement

Group-Fairness in Influence Maximization

Simplifying Graph Convolutional Networks

Measuring the Biases that Matter: The Ethical and Casual Foundations for Measures of Fairness in Algorithms

Guarantees for Spectral Clustering with Fairness Constraints

Putting Fairness Principles into Practice: Challenges, Metrics, and Improvements

Taking Advantage of Multitask Learning for Fair Classification

Predict then Propagate: Graph Neural Networks meet Personalized PageRank

Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals

Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees

iFair: Learning Individually Fair Data Representations for Algorithmic Decision Making

Conditional Network Embeddings

Fairness Through Computationally-Bounded Awareness

Learning Adversarially Fair and Transferable Representations

Graph Attention Networks

Personalized Job Recommendation System at LinkedIn: Practical Challenges and Lessons Learned

Decoupled Classifiers for Group-Fair and Efficient Machine Learning

Inductive Representation Learning on Large Graphs

Fair Inference on Outcomes

Counterfactual Fairness

DANCer: dynamic attributed networks with community structure generation

Equality of Opportunity in Supervised Learning

Semi-Supervised Classification with Graph Convolutional Networks

node2vec: Scalable Feature Learning for Networks

Censoring Representations with an Adversary

The Variational Fair Autoencoder

LINE: Large-scale Information Network Embedding

DeepWalk: online learning of social representations

Stochastic Backpropagation and Approximate Inference in Deep Generative Models

Auto-Encoding Variational Bayes

Learning Fair Representations

Learning to Discover Social Circles in Ego Networks

Fairness through awareness

Node Classification in Social Networks