Search Results for author: Xueru Zhang

Found 15 papers, 6 papers with code

Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithms

no code implementations ICML 2018 Xueru Zhang, Mohammad Mahdi Khalili, Mingyan Liu

Alternating direction method of multiplier (ADMM) is a popular method used to design distributed versions of a machine learning algorithm, whereby local computations are performed on local data with the output exchanged among neighbors in an iterative fashion.

Recycled ADMM: Improve Privacy and Accuracy with Less Computation in Distributed Algorithms

no code implementations7 Oct 2018 Xueru Zhang, Mohammad Mahdi Khalili, Mingyan Liu

Alternating direction method of multiplier (ADMM) is a powerful method to solve decentralized convex optimization problems.

Group Retention when Using Machine Learning in Sequential Decision Making: the Interplay between User Dynamics and Fairness

no code implementations NeurIPS 2019 Xueru Zhang, Mohammad Mahdi Khalili, Cem Tekin, Mingyan Liu

Machine Learning (ML) models trained on data from multiple demographic groups can inherit representation disparity (Hashimoto et al., 2018) that may exist in the data: the model may be less favorable to groups contributing less to the training process; this in turn can degrade population retention in these groups over time, and exacerbate representation disparity in the long run.

Decision Making Fairness

Recycled ADMM: Improving the Privacy and Accuracy of Distributed Algorithms

no code implementations8 Oct 2019 Xueru Zhang, Mohammad Mahdi Khalili, Mingyan Liu

It can be shown that the privacy-accuracy tradeoff can be improved significantly compared with conventional ADMM.

Fairness in Learning-Based Sequential Decision Algorithms: A Survey

no code implementations14 Jan 2020 Xueru Zhang, Mingyan Liu

However, in practice most decision-making processes are of a sequential nature, where decisions made in the past may have an impact on future data.

Decision Making Fairness

How Do Fair Decisions Fare in Long-term Qualification?

1 code implementation NeurIPS 2020 Xueru Zhang, Ruibo Tu, Yang Liu, Mingyan Liu, Hedvig Kjellström, Kun Zhang, Cheng Zhang

Our results show that static fairness constraints can either promote equality or exacerbate disparity depending on the driving factor of qualification transitions and the effect of sensitive attributes on feature distributions.

Decision Making Fairness

Improving Fairness and Privacy in Selection Problems

no code implementations7 Dec 2020 Mohammad Mahdi Khalili, Xueru Zhang, Mahed Abroshan, Somayeh Sojoudi

In this work, we study the possibility of using a differentially private exponential mechanism as a post-processing step to improve both fairness and privacy of supervised learning models.

Decision Making Fairness

Cardiac Complication Risk Profiling for Cancer Survivors via Multi-View Multi-Task Learning

1 code implementation25 Sep 2021 Thai-Hoang Pham, Changchang Yin, Laxmi Mehta, Xueru Zhang, Ping Zhang

In particular, MuViTaNet complements patient representation by using a multi-view encoder to effectively extract information by considering clinical data as both sequences of clinical visits and sets of clinical features.

Multi-Task Learning

Non-convex Optimization for Learning a Fair Predictor under Equalized Loss Fairness Constraint

no code implementations29 Sep 2021 Mohammad Mahdi Khalili, Xueru Zhang, Mahed Abroshan, Iman Vakilinia

In general, finding a fair predictor leads to a constrained optimization problem, and depending on the fairness notion, it may be non-convex.

Face Recognition Fairness

Fair Sequential Selection Using Supervised Learning Models

1 code implementation NeurIPS 2021 Mohammad Mahdi Khalili, Xueru Zhang, Mahed Abroshan

This observation implies that the fairness notions used in classification problems are not suitable for a selection problem where the applicants compete for a limited number of positions.

Fairness

Fairness and Accuracy under Domain Generalization

1 code implementation30 Jan 2023 Thai-Hoang Pham, Xueru Zhang, Ping Zhang

Although many approaches have been proposed to make ML models fair, they typically rely on the assumption that data distributions in training and deployment are identical.

Domain Generalization Fairness +1

Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shifts

no code implementations8 May 2023 Kun Jin, Tongxin Yin, Zhongzhu Chen, Zeyu Sun, Xueru Zhang, Yang Liu, Mingyan Liu

We consider a federated learning (FL) system consisting of multiple clients and a server, where the clients aim to collaboratively learn a common decision model from their distributed data.

Federated Learning

Federated Learning with Reduced Information Leakage and Computation

no code implementations10 Oct 2023 Tongxin Yin, Xueru Zhang, Mohammad Mahdi Khalili, Mingyan Liu

Federated learning (FL) is a distributed learning paradigm that allows multiple decentralized clients to collaboratively learn a common model without sharing local data.

Federated Learning Privacy Preserving

Loss Balancing for Fair Supervised Learning

1 code implementation7 Nov 2023 Mohammad Mahdi Khalili, Xueru Zhang, Mahed Abroshan

Imposing EL on the learning process leads to a non-convex optimization problem even if the loss function is convex, and the existing fair learning algorithms cannot properly be adopted to find the fair predictor under the EL constraint.

Face Recognition Fairness

Counterfactually Fair Representation

1 code implementation NeurIPS 2023 Zhiqun Zuo, Mohammad Mahdi Khalili, Xueru Zhang

It was shown in \cite{kusner2017counterfactual} that a sufficient condition for satisfying CF is to \textbf{not} use features that are descendants of sensitive attributes in the causal graph.

counterfactual Fairness

Cannot find the paper you are looking for? You can Submit a new open access paper.