Matches in SemOpenAlex for { <https://semopenalex.org/work/W4221148878> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4221148878 abstract "Deep learning models have been deployed in an increasing number of edge and mobile devices to provide healthcare. These models rely on training with a tremendous amount of labeled data to achieve high accuracy. However, for medical applications such as dermatological disease diagnosis, the private data collected by mobile dermatology assistants exist on distributed mobile devices of patients, and each device only has a limited amount of data. Directly learning from limited data greatly deteriorates the performance of learned models. Federated learning (FL) can train models by using data distributed on devices while keeping the data local for privacy. Existing works on FL assume all the data have ground-truth labels. However, medical data often comes without any accompanying labels since labeling requires expertise and results in prohibitively high labor costs. The recently developed self-supervised learning approach, contrastive learning (CL), can leverage the unlabeled data to pre-train a model, after which the model is fine-tuned on limited labeled data for dermatological disease diagnosis. However, simply combining CL with FL as federated contrastive learning (FCL) will result in ineffective learning since CL requires diverse data for learning but each device only has limited data. In this work, we propose an on-device FCL framework for dermatological disease diagnosis with limited labels. Features are shared in the FCL pre-training process to provide diverse and accurate contrastive information. After that, the pre-trained model is fine-tuned with local labeled data independently on each device or collaboratively with supervised federated learning on all devices. Experiments on dermatological disease datasets show that the proposed framework effectively improves the recall and precision of dermatological disease diagnosis compared with state-of-the-art methods." @default.
- W4221148878 created "2022-04-03" @default.
- W4221148878 creator A5000141831 @default.
- W4221148878 creator A5002340105 @default.
- W4221148878 creator A5005105786 @default.
- W4221148878 creator A5010433296 @default.
- W4221148878 creator A5013905128 @default.
- W4221148878 creator A5027969288 @default.
- W4221148878 creator A5045262387 @default.
- W4221148878 creator A5066534595 @default.
- W4221148878 date "2022-02-13" @default.
- W4221148878 modified "2023-10-18" @default.
- W4221148878 title "Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learning" @default.
- W4221148878 doi "https://doi.org/10.48550/arxiv.2202.07470" @default.
- W4221148878 hasPublicationYear "2022" @default.
- W4221148878 type Work @default.
- W4221148878 citedByCount "0" @default.
- W4221148878 crossrefType "posted-content" @default.
- W4221148878 hasAuthorship W4221148878A5000141831 @default.
- W4221148878 hasAuthorship W4221148878A5002340105 @default.
- W4221148878 hasAuthorship W4221148878A5005105786 @default.
- W4221148878 hasAuthorship W4221148878A5010433296 @default.
- W4221148878 hasAuthorship W4221148878A5013905128 @default.
- W4221148878 hasAuthorship W4221148878A5027969288 @default.
- W4221148878 hasAuthorship W4221148878A5045262387 @default.
- W4221148878 hasAuthorship W4221148878A5066534595 @default.
- W4221148878 hasBestOaLocation W42211488781 @default.
- W4221148878 hasConcept C108583219 @default.
- W4221148878 hasConcept C119857082 @default.
- W4221148878 hasConcept C136389625 @default.
- W4221148878 hasConcept C136764020 @default.
- W4221148878 hasConcept C153083717 @default.
- W4221148878 hasConcept C154945302 @default.
- W4221148878 hasConcept C186967261 @default.
- W4221148878 hasConcept C2776145971 @default.
- W4221148878 hasConcept C2992525071 @default.
- W4221148878 hasConcept C41008148 @default.
- W4221148878 hasConcept C50644808 @default.
- W4221148878 hasConceptScore W4221148878C108583219 @default.
- W4221148878 hasConceptScore W4221148878C119857082 @default.
- W4221148878 hasConceptScore W4221148878C136389625 @default.
- W4221148878 hasConceptScore W4221148878C136764020 @default.
- W4221148878 hasConceptScore W4221148878C153083717 @default.
- W4221148878 hasConceptScore W4221148878C154945302 @default.
- W4221148878 hasConceptScore W4221148878C186967261 @default.
- W4221148878 hasConceptScore W4221148878C2776145971 @default.
- W4221148878 hasConceptScore W4221148878C2992525071 @default.
- W4221148878 hasConceptScore W4221148878C41008148 @default.
- W4221148878 hasConceptScore W4221148878C50644808 @default.
- W4221148878 hasLocation W42211488781 @default.
- W4221148878 hasOpenAccess W4221148878 @default.
- W4221148878 hasPrimaryLocation W42211488781 @default.
- W4221148878 hasRelatedWork W2905852111 @default.
- W4221148878 hasRelatedWork W2907717662 @default.
- W4221148878 hasRelatedWork W3034749675 @default.
- W4221148878 hasRelatedWork W3172418599 @default.
- W4221148878 hasRelatedWork W4200017698 @default.
- W4221148878 hasRelatedWork W4205457357 @default.
- W4221148878 hasRelatedWork W4220686584 @default.
- W4221148878 hasRelatedWork W4221148878 @default.
- W4221148878 hasRelatedWork W4246751904 @default.
- W4221148878 hasRelatedWork W4289792623 @default.
- W4221148878 isParatext "false" @default.
- W4221148878 isRetracted "false" @default.
- W4221148878 workType "article" @default.