In the face of significant biodiversity decline, species distribution models (SDMs) are essential for understanding the impact of climate change on species habitats by connecting environmental conditions to species occurrences. Traditionally limited by a scarcity of species observations, these models have significantly improved in performance through the integration of larger datasets provided by citizen science initiatives. However, they still suffer from the strong class imbalance between species within these datasets, often resulting in the penalization of rare species--those most critical for conservation efforts. To tackle this issue, this study assesses the effectiveness of training deep learning models using a balanced presence-only loss function on large citizen science-based datasets. We demonstrate that this imbalance-aware loss function outperforms traditional loss functions across various datasets and tasks, particularly in accurately modeling rare species with limited observations.
Collaborative Optimization of Multiclass Imbalanced Learning: Density-Aware and Region-Guided Boosting
School of Mathematics and Computer, Guangdong Ocean University(数学与计算机学院,广东海洋大学);School of Automation Engineering, University of Electronic Science and Technology of China(自动化工程学院,电子科技大学)
针对标签噪声的学习是保证深度神经网络可靠性能的重要课题。目前的研究通常是指动态噪声建模与模型输出概率和损失值,然后分离干净和噪声样本。这些方法取得了显著的成功。然而,与精心挑选的数据不同,现有的方法在面对不平衡的数据集时往往不能很好地执行,这是现实世界中的常见情况。我们彻底调查了这一现象,并指出了阻碍性能的两个主要问题,即,\emph{inter-class loss distribution discrepancy}和\emph{misleading predictions due to uncertainty}。第一个问题是,现有的方法通常执行类不可知的噪声建模。然而,损失分布在类别不平衡的类别之间显示出显着的差异,并且类别不可知的噪声建模很容易与噪声样本和少数类别中的样本混淆。第二个问题是由于认知不确定性和任意不确定性,模型可能会输出误导性的预测,因此现有的方法,仅依赖于输出概率可能无法区分置信样本。受我们观察的启发,我们提出了一个不确定性感知的标签校正框架~(ULC)来处理不平衡数据集上的标签噪声。首先,我们进行认知不确定性感知类特定噪声建模,以识别值得信赖的干净样本,并完善/丢弃高度自信的真实/损坏的标签。然后,我们在后续的学习过程中引入任意的不确定性,以防止在标签噪声建模过程中的噪声积累。我们在几个合成和真实世界的数据集上进行实验。实验结果证明了该方法的有效性,特别是在…
Class-Imbalanced-Aware Adaptive Dataset Distillation for Scalable Pretrained Model on Credit Scoring
Risk Management Division, China Development Bank(国家开发银行风险管理部);School of Finance, Central University of Finance and Economics(中央财经大学金融学院);GF Holdings (Hong Kong) Corporation Limited(广发控股(香港)有限公司);University of Cambridge(剑桥大学)
SAGE: A sampling-aware global evaluation benchmark for species distribution modeling
University of Zurich(苏黎世大学);École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院);Swiss Federal Institute for Forest, Snow and Landscape Research, WSL(瑞士联邦森林、雪与景观研究所);ETH Zürich(苏黎世联邦理工学院)
Evaluation of AutoML Frameworks for IDS under Imbalanced Data Conditions of the NSL-KDD Dataset
Cybersecurity and Artificial Intelligence Laboratory (CS&I Lab), National Institute of Telecommunications (Inatel)(网络安全与人工智能实验室(CS&I Lab),国家电信研究所(Inatel));Wireless and Artificial Intelligence Laboratory (WAI Lab), National Institute of Telecommunications (Inatel)(无线与人工智能实验室(WAI Lab),国家电信研究所(Inatel))
Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction
Duke University(杜克大学);University of Maryland, College Park(马里兰大学帕克分校);George Mason University(乔治梅森大学);Yale University(耶鲁大学);The State University of New York at Buffalo(纽约州立大学布法罗分校)
Rebalanced Multimodal Learning with Data-aware Unimodal Sampling
School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院);School of Computer Science and Technology, Zhejiang Sci-Tech University(浙江理工大学计算机科学与技术学院);School of Computer Science and Communication Engineering, Jiangsu University(江苏大学计算机科学与通信工程学院)
T2ID-CAS: Diffusion Model and Class Aware Sampling to Mitigate Class Imbalance in Neck Ultrasound Anatomical Landmark Detection
Department of Computer Science, University of Central Florida(计算机科学系,中央佛罗里达大学);Department of Otolaryngology Head Neck Surgery, University of Cincinnati College of Medicine(耳鼻喉科与头颈外科系,辛辛那提大学医学院);Department of Internal Medicine, University of Central Florida College of Medicine(内科系,中央佛罗里达大学医学院)
Uncertainty-aware Pseudo-label Selection for Positive-Unlabeled Learning
Ludwig-Maximilians-Universität München(慕尼黑大学);Helmholtz Zentrum München—German Research Center for Environmental Health(亥姆霍兹慕尼黑中心——德国环境健康研究中心);Munich Center for Machine Learning(慕尼黑机器学习中心);Fraunhofer Institute for Integrated Circuits IIS(弗劳恩霍夫集成电路研究所);Technical University of Munich(慕尼黑工业大学)
Scaffold-Aware Generative Augmentation and Reranking for Enhanced Virtual Screening
Yale University(耶鲁大学);University of Oregon(俄勒冈大学);Broad Institute of MIT and Harvard(MIT和哈佛大学Broad研究所);Leipzig University(莱比锡大学);Vanderbilt University(范德比大学)
FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data
Harvard University(哈佛大学);University of Pennsylvania(宾夕法尼亚大学);Rutgers University(罗格斯大学);University of Washington(华盛顿大学);Kaiser Permanente Washington Health Research Institute(凯撒医疗华盛顿健康研究所);Stanford University(斯坦福大学)