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

Maarten, Buyl,; Bie, Tijl De

doi:10.1007/978-3-030-86520-7_22

Cited by 14 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…See Guedj [14] for details. 6 Theorem 1 also holds when we substitute L γ/2 m (h) and L γ/2 m (Q) as L γ m (h) and L γ m (Q) respectively. But we state the theorem in this form to ease the development of the later analysis.…”

Section: General Pac-bayesian Theorems For Subgroup Generalizationmentioning

confidence: 73%

“…A major factor that affects the generalization bound ( 6) is m , the distance from the target subgroup V m to the training set V 0 . The generalization bound (6) suggests that there is a better generalization guarantee for subgroups that are closer to the training set. In other words, it is unfair for subgroups that are far away from the training set.…”

Section: Implications For Fairness Of Graph Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Subgroup Generalization and Fairness of Graph Neural Networks

Deng

Mei

2021

Preprint

View full text Add to dashboard Cite

Despite enormous successful applications of graph neural networks (GNNs) recently, theoretical understandings of their generalization ability, especially for node-level tasks where data are not independent and identically-distributed (IID), have been sparse. The theoretical investigation of the generalization performance is beneficial for understanding fundamental issues (such as fairness) of GNN models and designing better learning methods. In this paper, we present a novel PAC-Bayesian analysis for GNNs under a non-IID semi-supervised learning setup. Moreover, we analyze the generalization performances on different subgroups of unlabeled nodes, which allows us to further study an accuracy-(dis)parity-style (un)fairness of GNNs from a theoretical perspective. Under reasonable assumptions, we demonstrate that the distance between a test subgroup and the training set can be a key factor affecting the GNN performance on that subgroup, which calls special attention to the training node selection for fair learning. Experiments across multiple GNN models and datasets support our theoretical results.

show abstract

Section: General Pac-bayesian Theorems For Subgroup Generalizationmentioning

confidence: 73%

Section: Implications For Fairness Of Graph Neural Networkmentioning

confidence: 99%

Subgroup Generalization and Fairness of Graph Neural Networks

Deng

Mei

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Additionally, regularization based on the network topology is also widely employed in link prediction. As an example, Buyl et al [24] proposed a fairness regularization term for the link prediction task. They first defined a set of probabilistic graph models that are fair w.r.t.…”

Section: Improving Group Fairnessmentioning

confidence: 99%

“…We collect these open-source datasets in https://github.com/ yushundong/Graph-Mining-Fairness-Data. [5], [24], [37], [39], [44], [73], [78], [80] [83], [87], [101], [128], [146] 7), [24], [25], [54], [114] occupation (21) MovieLens-1M [62] group, individual, 10,000 1,000,000 11 gender (2), age (7), [1], [18], [21], [33], [46], [54] popularity, provider, occupation (21) [71], [76], [97], [99], [105] social, user [159], [164], [171], [174], [175] MovieLens-20M [62] popularity 165,000 20,000,000 6 - [84], [157] C3…”

Section: Benchmark Datasetsmentioning

confidence: 99%

Fairness in Graph Mining: A Survey

Dong¹,

Ma²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Graph mining algorithms have been playing a significant role in myriad fields over the years. However, despite their promising performance on various graph analytical tasks, most of these algorithms lack fairness considerations. As a consequence, they could lead to discrimination towards certain populations when exploited in human-centered applications. Recently, algorithmic fairness has been extensively studied in graph-based applications. In contrast to algorithmic fairness on independent and identically distributed (i.i.d.) data, fairness in graph mining has exclusive backgrounds, taxonomies, and fulfilling techniques. In this survey, we provide a comprehensive and up-to-date introduction of existing literature under the context of fair graph mining. Specifically, we propose a novel taxonomy of fairness notions on graphs, which sheds light on their connections and differences. We further present an organized summary of existing techniques that promote fairness in graph mining. Finally, we summarize the widely used datasets in this emerging research field and provide insights on current research challenges and open questions, aiming at encouraging cross-breeding ideas and further advances.

show abstract

“…Finally Fairness Regularizer (FIPR) [12] generalizes the idea of DeBayes by proposing a regularization term to encourage fair link prediction that can be applied with any probabilistic network models. This regularizer is defined by the KL-divergence between the probabilistic node embedding model and its I-projection.…”

Section: P(𝑐mentioning

confidence: 99%

A Survey on Fairness for Machine Learning on Graphs

Choudhary¹,

Laclau²,

Largeron³

2022

Preprint

View full text Add to dashboard Cite

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. We hope that this survey will motivate researchers to tackle these issues in the near future and believe that it could be attractive to researchers and practitioners in areas including data mining, artificial intelligence and social science.

show abstract

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

Cited by 14 publications

References 22 publications

Subgroup Generalization and Fairness of Graph Neural Networks

Subgroup Generalization and Fairness of Graph Neural Networks

Fairness in Graph Mining: A Survey

A Survey on Fairness for Machine Learning on Graphs

Contact Info

Product

Resources

About