Analyzing Deep Neural Networks with Noisy Labels

Lim, Chong Hooi; Han, Sangwoo; Lee, Jongwuk

doi:10.1109/bigcomp48618.2020.00012

Cited by 3 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The diagnosis of MDD depends on the subjective evaluation of nine different symptoms and as little as one symptom may overlap between two patients [32], comorbidity is common, and symptoms may overlap with other disorders [33], leading to low interrater reliability of the diagnosis [34]. Such uncertainty associated with the diagnosis can obscure the relationship between a patient's data and the category it belongs to [35][36][37][38], and thereby decrease accuracy [39]. Datadriven definition of the disorder and the use of biotypes could help arrive at more homogeneous psychiatric groups.…”

Section: Discussionmentioning

confidence: 99%

Functional connectivity signatures of major depressive disorder: machine learning analysis of two multicenter neuroimaging studies

et al. 2023

View full text Add to dashboard Cite

The promise of machine learning has fueled the hope for developing diagnostic tools for psychiatry. Initial studies showed high accuracy for the identification of major depressive disorder (MDD) with resting-state connectivity, but progress has been hampered by the absence of large datasets. Here we used regular machine learning and advanced deep learning algorithms to differentiate patients with MDD from healthy controls and identify neurophysiological signatures of depression in two of the largest resting-state datasets for MDD. We obtained resting-state functional magnetic resonance imaging data from the REST-meta-MDD (N = 2338) and PsyMRI (N = 1039) consortia. Classification of functional connectivity matrices was done using support vector machines (SVM) and graph convolutional neural networks (GCN), and performance was evaluated using 5-fold cross-validation. Features were visualized using GCN-Explainer, an ablation study and univariate t-testing. The results showed a mean classification accuracy of 61% for MDD versus controls. Mean accuracy for classifying (non-)medicated subgroups was 62%. Sex classification accuracy was substantially better across datasets (73–81%). Visualization of the results showed that classifications were driven by stronger thalamic connections in both datasets, while nearly all other connections were weaker with small univariate effect sizes. These results suggest that whole brain resting-state connectivity is a reliable though poor biomarker for MDD, presumably due to disease heterogeneity as further supported by the higher accuracy for sex classification using the same methods. Deep learning revealed thalamic hyperconnectivity as a prominent neurophysiological signature of depression in both multicenter studies, which may guide the development of biomarkers in future studies.

show abstract

Section: Discussionmentioning

confidence: 99%

Functional connectivity signatures of major depressive disorder: machine learning analysis of two multicenter neuroimaging studies

et al. 2023

View full text Add to dashboard Cite

show abstract

“…A large number of algorithms have been developed for learning with noisy labels. Small loss selection recently achieved great success on noise-robust deep learning following the widely used criterion: DNNs tend to learn simple patterns first, then gradually memorize all samples [11,12,13]. These methods treat samples with small training loss as clean ones.…”

Section: Introductionmentioning

confidence: 99%

Synergistic Network Learning and Label Correction for Noise-robust Image Classification

Chen¹,

Kong²,

Seibel³

et al. 2022

Preprint

View full text Add to dashboard Cite

Large training datasets almost always contain examples with inaccurate or incorrect labels. Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. To address this problem, we propose a robust label correction framework combining the ideas of small loss selection and noise correction, which learns network parameters and reassigns ground truth labels iteratively. Taking the expertise of DNNs to learn meaningful patterns before fitting noise, our framework first trains two networks over the current dataset with small loss selection. Based on the classification loss and agreement loss of two networks, we can measure the confidence of training data. More and more confident samples are selected for label correction during the learning process. We demonstrate our method on both synthetic and real-world datasets with different noise types and rates, including CIFAR-10, CIFAR-100 and Clothing1M, where our method outperforms the baseline approaches.

show abstract

Synergistic Network Learning and Label Correction for Noise-Robust Image Classification

Gong

Kong²,

Seibel

et al. 2022

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Analyzing Deep Neural Networks with Noisy Labels

Cited by 3 publications

References 6 publications

Functional connectivity signatures of major depressive disorder: machine learning analysis of two multicenter neuroimaging studies

Functional connectivity signatures of major depressive disorder: machine learning analysis of two multicenter neuroimaging studies

Synergistic Network Learning and Label Correction for Noise-robust Image Classification

Synergistic Network Learning and Label Correction for Noise-Robust Image Classification

Contact Info

Product

Resources

About