Xintao Wu

Achieving non-discrimination in data release

2016 · arXiv (Cornell University)

Discrimination discovery and prevention/removal are increasingly important tasks in data mining. Discrimination discovery aims to unveil discriminatory practices on the protected attribute (e.g., gender) by analyzing the dataset of historical decision records, and discrimination prevention …

AdvPL: Adversarial Personalized Learning

2020

The data generation sources are increasing in the past few years, such as mobile devices, embedded sensors, various intelligent equipment and so forth. These increasing data sources push the deployment of deep learning models in …

Fine-grained Anomaly Detection in Sequential Data via Counterfactual Explanations

2022 · arXiv (Cornell University)

Anomaly detection in sequential data has been studied for a long time because of its potential in various applications, such as detecting abnormal system behaviors from log data. Although many approaches can achieve good performance …

Few-shot Anomaly Detection and Classification Through Reinforced Data Selection

2022 · 2022 IEEE International Conference on Data Mining (ICDM)

Due to the scarcity of anomalies, deep anomaly detection models are predominately trained in an unsupervised or semi-supervised manner depending on the availability of a small number of labeled samples. Currently, most unsupervised approaches detect …

Local Differential Privacy in Graph Neural Networks: a Reconstruction Approach

2023 · arXiv (Cornell University)

Graph Neural Networks have achieved tremendous success in modeling complex graph data in a variety of applications. However, there are limited studies investigating privacy protection in GNNs. In this work, we propose a learning framework …

Achieving Distributive Justice in Federated Learning via Uncertainty Quantification

2025 · arXiv (Cornell University)

Client-level fairness metrics for federated learning are used to ensure that all clients in a federation either: a) have similar final performance on their local data distributions (i.e., client parity), or b) obtain final performance …

Fairness across domains: a unified fairness-aware framework for domain generalization and unsupervised adaptation

2026 · Frontiers in Big Data

Fairness in machine learning remains a critical challenge, particularly in the presence of domain shift. We propose a unified fairness-aware framework for both domain generalization (DG) and unsupervised domain adaptation (UDA), which jointly addresses domain …