Results 21 to 30 of about 4,590,312 (339)

FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneity [PDF]

International Joint Conference on Artificial Intelligence, 2023
Federated noisy label learning (FNLL) is emerging as a promising tool for privacy-preserving multi-source decentralized learning. Existing research, relying on the assumption of class-balanced global data, might be incapable to model complicated label ...
Nannan Wu, Li Yu, Xue Jiang, Kwang-Ting Cheng, Zengqiang Yan   +4 more
semanticscholar   +1 more source

Experimental Comparison of Classification Methods under Class Imbalance [PDF]

EAI Endorsed Transactions on Scalable Information Systems, 2021
The class imbalance problem is prevalent in many domains including medical, natural language processing, image recognition, economic and geographic areas etc.
Hui Chen, Mengru Ji
doaj   +1 more source

Few-Shot Learning With Class Imbalance

IEEE Transactions on Artificial Intelligence, 2023
Few-Shot Learning (FSL) algorithms are commonly trained through Meta-Learning (ML), which exposes models to batches of tasks sampled from a meta-dataset to mimic tasks seen during evaluation. However, the standard training procedures overlook the real-world dynamics where classes commonly occur at different frequencies. While it is generally understood
Mateusz Ochal, Massimiliano Patacchiola, Jose Vazquez, Amos Storkey 0001, Sen Wang 0002   +4 more
openaire   +3 more sources

A systematic study of the class imbalance problem in convolutional neural networks [PDF]

Neural Networks, 2017
In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks (CNNs) and compare frequently used methods to address the issue.
M. Buda, A. Maki, M. Mazurowski
semanticscholar   +1 more source

Class Uncertainty: A Measure to Mitigate Class Imbalance

CoRR, 2023
Class-wise characteristics of training examples affect the performance of deep classifiers. A well-studied example is when the number of training examples of classes follows a long-tailed distribution, a situation that is likely to yield sub-optimal performance for under-represented classes.
Zeynep Sonat Baltaci, Kemal Oksuz, Selim Kuzucu, Kivanc Tezoren, Berkin Kerim Konar, Alpay Ozkan, Emre Akbas, Sinan Kalkan   +7 more
openaire   +2 more sources

Impact of lightGBM hyperparameters on class imbalance [PDF]

Class imbalance is a common problem in Machine Learning (ML) that introduces bias during the training phase of ML models, compromising their accuracy and reliability. This problem is particularly critical in fields such as disease diagnosis and credit risk assessment, where it is crucial to accurately predict the minority class.
Caballero Castro, Joan
core   +4 more sources

ADASYN-LOF Algorithm for Imbalanced Tornado Samples

Atmosphere, 2022
Early warning and forecasting of tornadoes began to combine artificial intelligence (AI) and machine learning (ML) algorithms to improve identification efficiency in the past few years.
Zhipeng Qing, Qiangyu Zeng, Hao Wang, Yin Liu, Taisong Xiong, Shihao Zhang   +5 more
doaj   +1 more source

Class imbalance should not throw you off balance: Choosing the right classifiers and performance metrics for brain decoding with imbalanced data

bioRxiv, 2023
Machine learning (ML) is increasingly used in cognitive, computational and clinical neuroscience. The reliable and efficient application of ML requires a sound understanding of its subtleties and limitations.
Philipp Thölke, Yorguin-José Mantilla-Ramos, Hamza Abdelhedi, C. Maschke, Arthur Dehgan, Yann Harel, Anirudha Kemtur, L. M. Berrada, Myriam Sahraoui, Tammy Young, Antoine Bellemare Pépin, Clara El Khantour, Mathieu Landry, A. Pascarella, Vanessa Hadid, Etienne Combrisson, Jordan O’Byrne, Karim Jerbi   +17 more
semanticscholar   +1 more source

Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction [PDF]

International Conference on Machine Learning, 2022
Due to limited communication capacities of edge devices, most existing federated learning (FL) methods randomly select only a subset of devices to participate in training for each communication round. Compared with engaging all the available clients, the
Jianyi Zhang, Ang Li, Minxue Tang, Jingwei Sun, Xiang Chen, Fan Zhang, Chang Chen, Yiran Chen, H. Li   +8 more
semanticscholar   +1 more source

Class Imbalance Learning [PDF]

Advanced Computing and Communications, 2017
Data classification task assigns labels to data points using a model that is learned from a collection of pre-labeled data points. The Class Imbalance Learning (CIL) problem is concerned with the performance of classification algorithms in the presence of under-represented data and severe class distribution skews.
Sudarsun Santhiappan, Balaraman Ravindran   +1 more
openaire   +1 more source