Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 4 of 4 for “"label scarcity"”.

  1. Towards Data Efficiency and Controllable Representations for Deep Learning in Resource-Constrained Domains

    … NLP settings, faces two fundamental challenges: label scarcity and data scarcity. Label scarcity stems from the high cost of expert annotation, the scarcity of domain experts, and the infeasibility of crowdsourcing, particularly in complex tasks requiring specialised knowledge. In parallel, data …

    passau-thes Repository record for Towards Data Efficiency and Controllable Representations for Deep Learning in Resource-Constrained Domains (opens in a new tab)

  2. Federated Learning With Generalization To New Domains

    … address the challenges of data heterogeneity and label scarcity in FL by proposing two novel approaches for federated domain generalization in both unsupervised and supervised settings. First, to tackle federated domain generalization in an unsupervised setting, we introduce Federated Unsupervised …

    queens Repository record for Federated Learning With Generalization To New Domains (opens in a new tab)

  3. Machine Learning Approaches that Extend Healthcare: Algorithms & Applications

    … identified until they reach advanced stages. The scarcity of specialists and disparities in healthcare access further complicate the long-term monitoring, timely intervention, and unbiased assessments. This thesis addresses the above challenges by developing artificial intelligence (AI) and …

    mit Repository record for Machine Learning Approaches that Extend Healthcare: Algorithms & Applications (opens in a new tab)

  4. Toward effective and generalisable machine learning for biosignal time series

    … contain missing values, and lack sufficient labels. In contrast, existing state-of-the-art methods are typically developed and validated on clean, regularly sampled biosignals with clinically verified ground-truth annotations, which limits their effectiveness and leads to performance …

    cambridge Repository record for Toward effective and generalisable machine learning for biosignal time series (opens in a new tab)