Noisy training labels can hurt model performance. Most approaches that aim to address label noise assume label noise is independent from the input features. In practice, however, label noise is often feature or \textit{instance-dependent}, and therefore biased (i.e., some instances are more likely to be mislabeled than others). E.g., in clinical care, female patients are more likely to be under-diagnosed for cardiovascular disease compared to male patients. Approaches that ignore this dependence can produce models with poor discriminative performance, and in many healthcare settings, can exacerbate issues around health disparities. In light of these limitations, we propose a two-stage approach to learn in the presence instance-dependent label noise. Our approach utilizes \textit{\anchor points}, a small subset of data for which we know the observed and ground truth labels. On several tasks, our approach leads to consistent improvements over the state-of-the-art in discriminative performance (AUROC) while mitigating bias (area under the equalized odds curve, AUEOC). For example, when predicting acute respiratory failure onset on the MIMIC-III dataset, our approach achieves a harmonic mean (AUROC and AUEOC) of 0.84 (SD [standard deviation] 0.01) while that of the next best baseline is 0.81 (SD 0.01). Overall, our approach improves accuracy while mitigating potential bias compared to existing approaches in the presence of instance-dependent label noise.
MaViLS, a Benchmark Dataset for Video-to-Slide Alignment, Assessing Baseline Accuracy with a Multimodal Alignment Algorithm Leveraging Speech, OCR, and Visual Features
Karlsruhe University of Applied Sciences(卡尔斯鲁厄应用技术大学);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);University of Hohenheim(霍恩海姆大学)
GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection
Ludwig-Maximilians-Universität München(慕尼黑莱布尼茨大学);University of Pittsburgh(匹兹堡大学);Harvard University(哈佛大学);University of Tromso(特罗姆斯大学);DLR-German Aerospace Center(德国航空航天中心);Munich Center for Machine Learning(慕尼黑机器学习中心)
Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation
School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院);Zhongguancun Laboratory(中关村实验室);Sichuan University(四川大学);University at Buffalo(纽约州立大学布法罗分校)
Leveraging Machine Unlearning for Cost-Efficient Preference Alignment
College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);School of Communication Engineering, Hangzhou Dianzi University(杭州电子科技大学通信工程学院)
Guided Manifold Alignment with Geometry-Regularized Twin Autoencoders
Department of Statistics(统计学系);Department of Computer Science(计算机科学系);Neuroscience Center(神经科学中心);Neuroscience Center and Department of Psychology(神经科学中心和心理学系);Department of Psychology(心理学系)
DGR: Tackling Drifted and Correlated Noise in Quantum Error Correction via Decoding Graph Re-weighting
Massachusetts Institute of Technology(麻省理工学院);Carnegie Mellon University(卡内基梅隆大学);Cornell University(康奈尔大学);Arizona State University(亚利桑那州立大学);University of Texas at Austin(德克萨斯大学奥斯汀分校);University of Chicago(芝加哥大学)