arXiv subjects

Cyrus DiCiccio

Publications and source records attributed to Cyrus DiCiccio.

7 recordsLinked to original sources

arXiv2024

From Models to Systems: A Comprehensive Fairness Framework for Compositional Recommender Systems

Fairness research in machine learning often centers on ensuring equitable performance of individual models. However, real-world recommendation systems are built on multiple models and even multiple stages, from candidate retrieval to scoring and serving, which raises challenges for responsible development and deployment. This system-level view, as highlighted by regulations like the EU AI Act, necessitates moving beyond auditing individual models as independent entities. We propose a holistic framework for modeling system-level fairness, focusing on the end-utility delivered to diverse user groups, and consider interactions between components such as retrieval and scoring models. We provide formal insights on the limitations of focusing solely on model-level fairness and highlight the need for alternative tools that account for heterogeneity in user preferences. To mitigate system-level disparities, we adapt closed-box optimization tools (e.g., BayesOpt) to jointly optimize utility and equity. We empirically demonstrate the effectiveness of our proposed framework on synthetic and real datasets, underscoring the need for a system-level framework.

cs.AI↗

arXiv2023

Detection and Mitigation of Algorithmic Bias via Predictive Rate Parity

Predictive parity (PP), also known as sufficiency, is a core definition of algorithmic fairness essentially stating that model outputs must have the same interpretation of expected outcomes regardless of group. Testing and satisfying PP is especially important in many settings where model scores are interpreted by humans or directly provide access to opportunity, such as healthcare or banking. Solutions for PP violations have primarily been studied through the lens of model calibration. However, we find that existing calibration-based tests and mitigation methods are designed for independent data, which is often not assumable in large-scale applications such as social media or medical testing. In this work, we address this issue by developing a statistically rigorous non-parametric regression based test for PP with dependent observations. We then apply our test to illustrate that PP testing can significantly vary under the two assumptions. Lastly, we provide a mitigation solution to provide a minimally-biased post-processing transformation function to achieve PP.

stat.ME↗

arXiv2022

Long-term Dynamics of Fairness Intervention in Connection Recommender Systems

Recommender system fairness has been studied from the perspectives of a variety of stakeholders including content producers, the content itself and recipients of recommendations. Regardless of which type of stakeholders are considered, most works in this area assess the efficacy of fairness intervention by evaluating a single fixed fairness criterion through the lens of a one-shot, static setting. Yet recommender systems constitute dynamical systems with feedback loops from the recommendations to the underlying population distributions which could lead to unforeseen and adverse consequences if not taken into account. In this paper, we study a connection recommender system patterned after the systems employed by web-scale social networks and analyze the long-term effects of intervening on fairness in the recommendations. We find that, although seemingly fair in aggregate, common exposure and utility parity interventions fail to mitigate amplification of biases in the long term. We theoretically characterize how certain fairness interventions impact the bias amplification dynamics in a stylized Pólya urn model.

cs.CY↗

arXiv2020

Personalized Treatment Selection using Causal Heterogeneity

Randomized experimentation (also known as A/B testing or bucket testing) is widely used in the internet industry to measure the metric impact obtained by different treatment variants. A/B tests identify the treatment variant showing the best performance, which then becomes the chosen or selected treatment for the entire population. However, the effect of a given treatment can differ across experimental units and a personalized approach for treatment selection can greatly improve upon the usual global selection strategy. In this work, we develop a framework for personalization through (i) estimation of heterogeneous treatment effect at either a cohort or member-level, followed by (ii) selection of optimal treatment variants for cohorts (or members) obtained through (deterministic or stochastic) constrained optimization. We perform a two-fold evaluation of our proposed methods. First, a simulation analysis is conducted to study the effect of personalized treatment selection under carefully controlled settings. This simulation illustrates the differences between the proposed methods and the suitability of each with increasing uncertainty. We also demonstrate the effectiveness of the method through a real-life example related to serving notifications at Linkedin. The solution significantly outperformed both heuristic solutions and the global treatment selection baseline leading to a sizable win on top-line metrics like member visits.

stat.ME↗

arXiv2020

Interpretable Assessment of Fairness During Model Evaluation

For companies developing products or algorithms, it is important to understand the potential effects not only globally, but also on sub-populations of users. In particular, it is important to detect if there are certain groups of users that are impacted differently compared to others with regard to business metrics or for whom a model treats unequally along fairness concerns. In this paper, we introduce a novel hierarchical clustering algorithm to detect heterogeneity among users in given sets of sub-populations with respect to any specified notion of group similarity. We prove statistical guarantees about the output and provide interpretable results. We demonstrate the performance of the algorithm on real data from LinkedIn.

cs.LG↗

arXiv2020

Evaluating Fairness Using Permutation Tests

Machine learning models are central to people's lives and impact society in ways as fundamental as determining how people access information. The gravity of these models imparts a responsibility to model developers to ensure that they are treating users in a fair and equitable manner. Before deploying a model into production, it is crucial to examine the extent to which its predictions demonstrate biases. This paper deals with the detection of bias exhibited by a machine learning model through statistical hypothesis testing. We propose a permutation testing methodology that performs a hypothesis test that a model is fair across two groups with respect to any given metric. There are increasingly many notions of fairness that can speak to different aspects of model fairness. Our aim is to provide a flexible framework that empowers practitioners to identify significant biases in any metric they wish to study. We provide a formal testing mechanism as well as extensive experiments to show how this method works in practice.

stat.AP↗

arXiv2020

A Framework for Fairness in Two-Sided Marketplaces

Many interesting problems in the Internet industry can be framed as a two-sided marketplace problem. Examples include search applications and recommender systems showing people, jobs, movies, products, restaurants, etc. Incorporating fairness while building such systems is crucial and can have a deep social and economic impact (applications include job recommendations, recruiters searching for candidates, etc.). In this paper, we propose a definition and develop an end-to-end framework for achieving fairness while building such machine learning systems at scale. We extend prior work to develop an optimization framework that can tackle fairness constraints from both the source and destination sides of the marketplace, as well as dynamic aspects of the problem. The framework is flexible enough to adapt to different definitions of fairness and can be implemented in very large-scale settings. We perform simulations to show the efficacy of our approach.

cs.AI↗