Research map / Label-efficient and robust learning / Recognition and long-tail

Learning from weak labelers as constraints

ICLR 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes learning from programmatic weak labelers by treating their outputs as constraints rather than modeling a latent generative model of weak labels and true labels.

Problem

Programmatic weak supervision, where weak labelers abstain or give noisy labels; prior latent generative label models rely on assumptions that may not hold.

Approach

Instead of modeling the joint distribution of weak labels and the latent true label, the method treats weak labeler outputs as constraints on the learned model, avoiding the strong assumptions of generative label models.

Closest papers by meaning

• Generative Modeling Helps Weak Supervision (and Vice Versa) (ICLR 2023 · similarity 0.92)
• Losses over Labels: Weakly Supervised Learning via Direct Loss Construction (AAAI 2023 · similarity 0.91)
• Label Propagation with Weak Supervision (ICLR 2023 · similarity 0.91)
• Fusing Conditional Submodular GAN and Programmatic Weak Supervision (AAAI 2024 · similarity 0.90)
• Weak Supervision Performance Evaluation via Partial Identification (NeurIPS 2024 · similarity 0.89)
• A General Framework for Learning from Weak Supervision (ICML 2024 · similarity 0.88)