Related papers: Differentially Private Fair Learning
Differential privacy (DP) is the standard for privacy-preserving analysis, and introduces a fundamental trade-off between privacy guarantees and model performance. Selecting the optimal balance is a critical challenge that can be framed as…
In blockchain systems, fair transaction ordering is crucial for a trusted and regulation-compliant economic ecosystem. Unlike traditional State Machine Replication (SMR) systems, which focus solely on liveness and safety, blockchain systems…
Differential privacy is a promising formal approach to data privacy, which provides a quantitative bound on the privacy cost of an algorithm that operates on sensitive information. Several tools have been developed for the formal…
Link prediction (LP) algorithms propose to each node a ranked list of nodes that are currently non-neighbors, as the most likely candidates for future linkage. Owing to increasing concerns about privacy, users (nodes) may prefer to keep…
Differential privacy is a popular privacy model within the research community because of the strong privacy guarantee it offers, namely that the presence or absence of any individual in a data set does not significantly influence the…
Fair ranking problems arise in many decision-making processes that often necessitate a trade-off between accuracy and fairness. Many existing studies have proposed correction methods such as adding fairness constraints to a ranking model's…
Differential privacy (DP) is a privacy-preserving paradigm that protects the training data when training deep learning models. Critically, the performance of models is determined by the training hyperparameters, especially those of the…
In modern settings of data analysis, we may be running our algorithms on datasets that are sensitive in nature. However, classical machine learning and statistical algorithms were not designed with these risks in mind, and it has been…
Federated Learning presents a way to revolutionize AI applications by eliminating the necessity for data sharing. Yet, research has shown that information can still be extracted during training, making additional privacy-preserving measures…
Following related work in law and policy, two notions of disparity have come to shape the study of fairness in algorithmic decision-making. Algorithms exhibit treatment disparity if they formally treat members of protected subgroups…
Kearns et al. [2018] recently proposed a notion of rich subgroup fairness intended to bridge the gap between statistical and individual notions of fairness. Rich subgroup fairness picks a statistical fairness constraint (say, equalizing…
Federated learning (FL) algorithms commonly aim to maximize clients' accuracy by training a model on their collective data. However, in several FL applications, the model's decisions should meet a group fairness constraint to be independent…
Machine learning models are often personalized with categorical attributes that are protected, sensitive, self-reported, or costly to acquire. In this work, we show models that are personalized with group attributes can reduce performance…
Discrimination via algorithmic decision making has received considerable attention. Prior work largely focuses on defining conditions for fairness, but does not define satisfactory measures of algorithmic unfairness. In this paper, we focus…
This project explores adversarial training techniques to develop fairer Deep Neural Networks (DNNs) to mitigate the inherent bias they are known to exhibit. DNNs are susceptible to inheriting bias with respect to sensitive attributes such…
Decision trees are interpretable models that are well-suited to non-linear learning problems. Much work has been done on extending decision tree learning algorithms with differential privacy, a system that guarantees the privacy of samples…
Data mining information about people is becoming increasingly important in the data-driven society of the 21st century. Unfortunately, sometimes there are real-world considerations that conflict with the goals of data mining; sometimes the…
Differentially private federated learning (DP-FL) enables clients to collaboratively train machine learning models while preserving the privacy of their local data. However, most existing DP-FL approaches assume that all clients share a…
Algorithmic predictions are increasingly used to inform the allocation of scarce resources. The promise of these methods is that, through machine learning, they can better identify the people who would benefit most from interventions.…
Strict privacy is of paramount importance in distributed machine learning. Federated learning, with the main idea of communicating only what is needed for learning, has been recently introduced as a general approach for distributed learning…