A comprehensive survey of few-shot learning: Evolution, applications, challenges, and opportunities

Y Song, T Wang, P Cai, SK Mondal… - ACM Computing Surveys, 2023 - dl.acm.org
Few-shot learning (FSL) has emerged as an effective learning method and shows great
potential. Despite the recent creative works in tackling FSL tasks, learning valid information …

A survey on deep learning for cybersecurity: Progress, challenges, and opportunities

M Macas, C Wu, W Fuertes - Computer Networks, 2022 - Elsevier
As the number of Internet-connected systems rises, cyber analysts find it increasingly difficult
to effectively monitor the produced volume of data, its velocity and diversity. Signature-based …

Large language models for cyber security: A systematic literature review

HX Xu, SA Wang, N Li, K Wang, Y Zhao, K Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
The rapid advancement of Large Language Models (LLMs) has opened up new
opportunities for leveraging artificial intelligence in various domains, including cybersecurity …

Few-shot learning with noisy labels

KJ Liang, SB Rangrej, V Petrovic… - Proceedings of the …, 2022 - openaccess.thecvf.com
Few-shot learning (FSL) methods typically assume clean support sets with accurately
labeled samples when training on novel classes. This assumption can often be unrealistic …

Few-shot hyperspectral image classification with self-supervised learning

Z Li, H Guo, Y Chen, C Liu, Q Du… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Recently, few-shot learning (FSL) has been introduced for hyperspectral image (HSI)
classification with few labeled samples. However, existing FSL-based HSI classification …

Neighborhood collective estimation for noisy label identification and correction

J Li, G Li, F Liu, Y Yu - European Conference on Computer Vision, 2022 - Springer
Learning with noisy labels (LNL) aims at designing strategies to improve model performance
and generalization by mitigating the effects of model overfitting to noisy labels. The key …

Context-enriched molecule representations improve few-shot drug discovery

J Schimunek, P Seidl, L Friedrich, D Kuhn… - arXiv preprint arXiv …, 2023 - arxiv.org
A central task in computational drug discovery is to construct models from known active
molecules to find further promising molecules for subsequent screening. However, typically …

Trans4E: Link prediction on scholarly knowledge graphs

M Nayyeri, GM Cil, S Vahdati, F Osborne, M Rahman… - Neurocomputing, 2021 - Elsevier
Abstract The incompleteness of Knowledge Graphs (KGs) is a crucial issue affecting the
quality of AI-based services. In the scholarly domain, KGs describing research publications …

Few-shot rolling bearing fault diagnosis with metric-based meta learning

S Wang, D Wang, D Kong, J Wang, W Li, S Zhou - Sensors, 2020 - mdpi.com
Fault diagnosis methods based on deep learning and big data have achieved good results
on rotating machinery. However, the conventional deep learning method of bearing fault …

[HTML][HTML] Deepfake forensics analysis: An explainable hierarchical ensemble of weakly supervised models

SH Silva, M Bethany, AM Votto, IH Scarff… - Forensic Science …, 2022 - Elsevier
Deepfakes have become exponentially more common and sophisticated in recent years, so
much so that forensic specialists, policy makers, and the public alike are anxious about their …