Yi Xu

Evaluating and Boosting Uncertainty Quantification in Classification

2019 · arXiv (Cornell University)

Emergence of artificial intelligence techniques in biomedical applications urges the researchers to pay more attention on the uncertainty quantification (UQ) in machine-assisted medical decision making. For classification tasks, prior studies on UQ are difficult to …

Optimal Bandwidth Allocation for Web Crawler Systems

2019

Web crawler is an important tool to obtain the information from the Internet in time. In a typical web crawler system with the limited bandwidth, there are many websites required to be crawled with different …

Self-Supervised Disentangled Embedding For Robust Image Classification

2021

Recently, the security of deep learning algorithms against adversarial samples has been widely recognized. Most of the existing defense methods only consider the attack influence on image level, while the effect of correlation among feature …

Near-perfect fidelity polarization-encoded multilayer optical data storage based on aligned gold nanorods

2021 · Opto-Electronic Advances

Encoding information in light polarization is of great importance in facilitating optical data storage (ODS) for information security and data storage capacity escalation. However, despite recent advances in nanophotonic techniques vastly enhancing the feasibility of …

SLA$^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation

2021 · arXiv (Cornell University)

Anomaly detection is a fundamental yet challenging problem in machine learning due to the lack of label information. In this work, we propose a novel and powerful framework, dubbed as SLA$^2$P, for unsupervised anomaly detection. …

SST: Semantic and Structural Transformers for Hierarchy-aware Language Models in E-commerce

2023

Hierarchies are common structures used to organize data, such as e-commerce hierarchies associated with product data. With these product hierarchies, we aim to learn hierarchy-aware product text embeddings to improve fine-tuning performance on a variety …

Efficient Data Valuation Approximation in Federated Learning: A Sampling-Based Approach

2025

Federated learning (FL) has emerged as a prominent distributed learning paradigm to utilize datasets across multiple data providers. In FL, cross-silo data providers often hesitate to share their high-quality dataset unless their data value can …