AUC maximization for low-resource named entity recognition

ND Nguyen, W Tan, L Du, W Buntine, R Beare… - Proceedings of the …, 2023 - ojs.aaai.org
Current work in named entity recognition (NER) uses either cross entropy (CE) or
conditional random fields (CRF) as the objective/loss functions to optimize the underlying …

Coltr: Semi-supervised learning to rank with co-training and over-parameterization for web search

Y Li, H **ong, Q Wang, L Kong, H Liu… - … on Knowledge and …, 2023 - ieeexplore.ieee.org
While learning to rank (LTR) has been widely used in web search to prioritize most relevant
webpages among the retrieved contents subject to the input queries, the traditional LTR …

Uncertainty-aware graph-based hyperspectral image classification

L Yu, Y Lou, F Chen - 2024 - par.nsf.gov
Hyperspectral imaging (HSI) technology captures spectral information across a broad
wavelength range, providing richer pixel features compared to traditional color images with …

Understanding and bridging the gap between unsupervised network representation learning and security analytics

J Xu, X Shu, Z Li - 2024 IEEE Symposium on Security and …, 2024 - ieeexplore.ieee.org
Cyber-attacks have become increasingly sophisticated, which also drives the development
of security analytics that produce countermeasures by mining organizational logs, eg …

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation

B Han, Q Xu, Z Yang, S Bao, P Wen, Y Jiang… - arxiv preprint arxiv …, 2024 - arxiv.org
The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level
long-tail learning problems. In the past two decades, many AUC optimization methods have …

DRAUC: an instance-wise distributionally robust AUC optimization framework

S Dai, Q Xu, Z Yang, X Cao… - Advances in Neural …, 2023 - proceedings.neurips.cc
Abstract The Area Under the ROC Curve (AUC) is a widely employed metric in long-tailed
classification scenarios. Nevertheless, most existing methods primarily assume that training …

Optimal large-scale stochastic optimization of NDCG surrogates for deep learning

ZH Qiu, Q Hu, Y Zhong, WW Tu, L Zhang, T Yang - Machine Learning, 2025 - Springer
In this paper, we introduce principled stochastic algorithms to efficiently optimize Normalized
Discounted Cumulative Gain (NDCG) and its top-K variant for deep models. To this end, we …

A self-supervised learning approach for registration agnostic imaging models with 3D brain CTA

Y Dong, S Pachade, X Liang, SA Sheth, L Giancardo - Iscience, 2024 - cell.com
Deep learning-based neuroimaging pipelines for acute stroke typically rely on image
registration, which not only increases computation but also introduces a point of failure. In …

Boosting Few-Shot Learning with Disentangled Self-Supervised Learning and Meta-Learning for Medical Image Classification

E Pachetti, SA Tsaftaris, S Colantonio - arxiv preprint arxiv:2403.17530, 2024 - arxiv.org
Background and objective: Employing deep learning models in critical domains such as
medical imaging poses challenges associated with the limited availability of training data …

AUC Optimization from Multiple Unlabeled Datasets

Z **e, Y Liu, M Li - Proceedings of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
Weakly supervised learning aims to make machine learning more powerful when the perfect
supervision is unavailable, and has attracted much attention from researchers. Among the …