Towards Fairness Exploration and Optimization for Digital Service Networks

Digital service networks often face the challenge of <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</b>ervice-<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</b>riented <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F</b>airness (SOF), where service nodes with varying levels of activity may receive unequal treatment. This article takes the recommendation service system as a representative case to explore and mitigate the impact of SOF. The SOF issue in the recommendation service system can be abstracted as <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">U</b>ser-<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</b>riented <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F</b>airness (UOF), where service models often exhibit bias toward a small group of users, resulting in significant unfairness in the quality of recommendations. Existing research on UOF faces three major limitations, and no single approach effectively addresses all of them. <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Limitation 1:</b> Post-processing methods fail to address the root cause of the UOF issue. <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Limitation 2:</b> Some in-processing methods rely heavily on unstable user similarity calculations under severe data sparsity problems. <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Limitation 3:</b> Other in-processing methods overlook the disparate treatment of individual users within user groups. In this article, we propose a novel <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">I</b>ndividual <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</b>eweighting for <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">U</b>ser-<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</b>riented <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F</b>airness framework, namely IR-UOF, to address all the aforementioned limitations. The motivation behind IR-UOF is to <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">introduce an in-processing strategy that addresses the UOF issue at the individual level without the need to explore user similarities.</i> We first conduct extensive experiments on three real-world recommendation service datasets using four backbone recommendation models to demonstrate the effectiveness of IR-UOF in mitigating UOF and improving recommendation fairness. Furthermore, we select two general digital service datasets to prove that IR-UOF can be extended to tackle the general SOF issue in other types of digital service networks. In summary, the IR-UOF framework achieves optimal model performance across all datasets, while improving fairness by at least 3.8% in recommendation systems and 24.7% in general service systems.