A general framework for learning from weak supervision

H Chen, J Wang, L Feng, X Li, Y Wang, X **-free automatic verbalizer for multi-class classification
Y Kho, J Kim, P Kang - arxiv preprint arxiv:2312.04982, 2023 - arxiv.org
Recently, prompt-based fine-tuning has garnered considerable interest as a core technique
for few-shot text classification task. This approach reformulates the fine-tuning objective to …

Learning from label proportions with instance-wise consistency

R Kobayashi, Y Mukuta, T Harada - arxiv preprint arxiv:2203.12836, 2022 - arxiv.org
Learning from Label Proportions (LLP) is a weakly supervised learning method that aims to
perform instance classification from training data consisting of pairs of bags containing …

Corruptions of Supervised Learning Problems: Typology and Mitigations

L Iacovissi, N Lu, RC Williamson - arxiv preprint arxiv:2307.08643, 2023 - arxiv.org
Corruption is notoriously widespread in data collection. Despite extensive research, the
existing literature on corruption predominantly focuses on specific settings and learning …