Label Learning Flows for Weakly Supervised Learning
This paper introduces Label Learning Flows (LLF), a novel framework for weakly supervised learning that leverages conditional normalizing flows to model the uncertainty in label estimation, outperforming existing deterministic methods in classification and regression tasks.
Complementary Label Learning without Assumptions: SCARCE Approach
SCARCE proposes a consistent approach for complementary-label learning without relying on distribution assumptions, showing superior performance.
Learning from Reduced Labels for Long-Tailed Data Analysis
Introducing Reduced Labels for Long-Tailed Data to preserve supervised information and decrease labeling costs.
SCARCE: A Novel Approach for Complementary-Label Learning
提案されたSCARCEアプローチは、均一な分布仮定や通常のラベルトレーニングセットに依存せず、一貫性のある補完ラベル学習を実現します。
RulePrompt: Weakly Supervised Text Classification with Prompting PLMs and Self-Iterative Logical Rules
The authors propose RulePrompt, a novel approach that leverages logical rules to enhance the understanding of categories in weakly supervised text classification tasks using prompting PLMs.
© 2024 by Linnk AI