Individual Fairness for Graph Neural Networks

Yushun Dong · Jian Li Kang · Hanghang Tong · Jundong Li

92 citations0/0 files storedACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Ethics and Social Impacts of AI Privacy-Preserving Technologies in Data Advanced Graph Neural Networks

Abstract

Recent years have witnessed the pivotal role of Graph Neural Networks (GNNs) in various high-stake decision-making scenarios due to their superior learning capability. Close on the heels of the successful adoption of GNNs in different application domains has been the increasing societal concern that conventional GNNs often do not have fairness considerations. Although some research progress has been made to improve the fairness of GNNs, these works mainly focus on the notion of group fairness regarding different subgroups defined by a protected attribute such as gender, age, and race. Beyond that, it is also essential to study the GNN fairness at a much finer granularity (i.e., at the node level) to ensure that GNNs render similar prediction results for similar individuals to achieve the notion of individual fairness. Toward this goal, in this paper, we make an initial investigation to enhance the individual fairness of GNNs and propose a novel ranking based framework---REDRESS. Specifically, we refine the notion of individual fairness from a ranking perspective, and formulate the ranking based individual fairness promotion problem. This naturally addresses the issue of Lipschitz constant specification and distance calibration resulted from the Lipschitz condition in the conventional individual fairness definition. Our proposed framework REDRESS encapsulates the GNN model utility maximization and the ranking-based individual fairness promotion in a joint framework to enable end-to-end training. It is noteworthy mentioning that REDRESS is a plug-and-play framework and can be easily generalized to any prevalent GNN architectures. Extensive experiments on multiple real-world graphs demonstrate the superiority of REDRESS in achieving a good balance between model utility maximization and individual fairness promotion. Our open source code can be found here: https://github.com/yushundong/REDRESS.

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 92 citations exist upstream.

References

2012Fairness through awareness 2016Equality of Opportunity in Supervised Learning 2008ArnetMiner 2015Certifying and Removing Disparate Impact 2013Learning Fair Representations 2020Fairness in Machine Learning 2019Fairwalk: Towards Fair Graph Embedding 2019iFair: Learning Individually Fair Data Representations for Algorithmic Decision Making

Cited by

2022Learning Fair Node Representations with Graph Counterfactual Fairness 2022GUIDE: Group Equality Informed Individual Fairness in Graph Neural Networks 2021Fair Graph Mining 2023Mitigating Multisource Biases in Graph Neural Networks via Real Counterfactual Samples 2023Towards Fair Financial Services for All: A Temporal GNN Approach for Individual Fairness on Transaction Networks

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.