A Multi-view Confidence-calibrated Framework for Fair and Stable Graph Representation Learning

Zhang, Xu; Zhang, Liang; Jin, Bo; Xia, Lu

doi:10.1109/icdm51629.2021.00194

Cited by 15 publications

(47 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our degree fairness is defined in a group-wise manner, which is in line with existing fairness definitions (Zafar et al 2017;Agarwal, Lakkaraju, and Zitnik 2021) and offers a flexible setup. On the one hand, a simple and practical scenario could involve just two groups, since typically the degree fairness issue is the most serious between nodes with the smallest and largest degrees.…”

Section: Problem Formulationmentioning

confidence: 99%

On Generalized Degree Fairness in Graph Neural Networks

Liu¹,

Nguyen²,

Fang³

2023

Preprint

View full text Add to dashboard Cite

Conventional graph neural networks (GNNs) are often confronted with fairness issues that may stem from their input, including node attributes and neighbors surrounding a node. While several recent approaches have been proposed to eliminate the bias rooted in sensitive attributes, they ignore the other key input of GNNs, namely the neighbors of a node, which can introduce bias since GNNs hinge on neighborhood structures to generate node representations. In particular, the varying neighborhood structures across nodes, manifesting themselves in drastically different node degrees, give rise to the diverse behaviors of nodes and biased outcomes. In this paper, we first define and generalize the degree bias using a generalized definition of node degree as a manifestation and quantification of different multi-hop structures around different nodes. To address the bias in the context of node classification, we propose a novel GNN framework called Generalized Degree Fairness-centric Graph Neural Network (Deg-FairGNN). Specifically, in each GNN layer, we employ a learnable debiasing function to generate debiasing contexts, which modulate the layer-wise neighborhood aggregation to eliminate the degree bias originating from the diverse degrees among nodes. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our model on both accuracy and fairness metrics.

show abstract

Section: Problem Formulationmentioning

confidence: 99%

On Generalized Degree Fairness in Graph Neural Networks

Liu¹,

Nguyen²,

Fang³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, there has been a line of works [3], [104], [173] that extend counterfactual fairness from traditional i.i.d. data to graph data.…”

Section: Counterfactual Fairnessmentioning

confidence: 99%

“…To measure counterfactual fairness on graphs, recent works [3], [173] usually adopt Unfairness Score, which is the percentage of nodes whose predicted label changes when their sensitive feature values are changed (while other features are fixed). Beyond that, Ma et al [104] also proposed to evaluate graph counterfactual fairness by measuring the average prediction discrepancy between any two different versions of counterfactual sensitive feature assignment on all the n nodes.…”

Section: Counterfactual Fairnessmentioning

confidence: 99%

“…German [9] group, couterfactual 1,000 21,742 27 gender (2) [3], [40], [173] NBA [38] group 403 10,621 96 country (2) [38], [67] Recividism [69] group, individual 18,876 311,870 18 race (2) [3], [40], [44], [104], [173] couterfactual Credit [168] group, couterfactual 30,000 1,421,858 13 age (2) [3], [40], [104], [173] in different real-world applications [23], [28], [134], [158], [169]. Although we have surveyed many fairness notions for graph mining, we need to admit that by no means are they complete, as other types of biases could also exist, depending on the needs of different real-world scenarios [160].…”

Section: C4mentioning

confidence: 99%

See 1 more Smart Citation

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

“…Most defense mechanisms focus on mitigating adversarial attacks by e.g. graph sanitization [53], adversarial training [12], [59], and certification of robustness [6]. On the other hand, to defend against privacy attacks, one of the most popular proposed countermeasures is differential privacy (DP) [14].…”

Section: Defense Of Attacks On Gnnsmentioning

confidence: 99%

Model Inversion Attacks against Graph Neural Networks

Zhang¹,

Liu²,

Huang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Many data mining tasks rely on graphs to model relational structures among individuals (nodes). Since relational data are often sensitive, there is an urgent need to evaluate the privacy risks in graph data. One famous privacy attack against data analysis models is the model inversion attack, which aims to infer sensitive data in the training dataset and leads to great privacy concerns. Despite its success in grid-like domains, directly applying model inversion attacks on non-grid domains such as graph leads to poor attack performance. This is mainly due to the failure to consider the unique properties of graphs. To bridge this gap, we conduct a systematic study on model inversion attacks against Graph Neural Networks (GNNs), one of the state-of-the-art graph analysis tools in this paper. Firstly, in the white-box setting where the attacker has full access to the target GNN model, we present GraphMI to infer the private training graph data. Specifically in GraphMI, a projected gradient module is proposed to tackle the discreteness of graph edges and preserve the sparsity and smoothness of graph features; a graph auto-encoder module is used to efficiently exploit graph topology, node attributes, and target model parameters for edge inference; a random sampling module can finally sample discrete edges. Furthermore, in the hard-label black-box setting where the attacker can only query the GNN API and receive the classification results, we propose two methods based on gradient estimation and reinforcement learning (RL-GraphMI). With the proposed methods, we study the connection between model inversion risk and edge influence and show that edges with greater influence are more likely to be recovered. Extensive experiments over several public datasets demonstrate the effectiveness of our methods. We also evaluate our attacks under two defenses: one is the well-designed differential private training, and the other is graph preprocessing. Our experimental results show that such defenses are not sufficiently effective and call for more advanced defenses against privacy attacks.

show abstract

A Multi-view Confidence-calibrated Framework for Fair and Stable Graph Representation Learning

Cited by 15 publications

References 8 publications

On Generalized Degree Fairness in Graph Neural Networks

On Generalized Degree Fairness in Graph Neural Networks

Fairness in Graph Mining: A Survey

Model Inversion Attacks against Graph Neural Networks

Contact Info

Product

Resources

About