Research map / Label-efficient and robust learning / Semi-supervised learning

Uncertainty-Informed Meta Pseudo Labeling for Surrogate Modeling with Limited Labeled Data

NeurIPS 2025 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 0 citations (OpenAlex)

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 an uncertainty-informed meta pseudo labeling approach for semi-supervised surrogate modeling with neural operators, aiming to reduce reliance on labeled simulation data.

Problem

Surrogate modeling with neural operators needs large labeled datasets that are costly to obtain; semi-supervised learning using unlabeled data is vulnerable to noisy pseudo-labels.

Approach

Combines meta pseudo labeling with uncertainty information so that pseudo-labels are weighted or filtered by model uncertainty, mitigating the effect of noisy pseudo-labels in semi-supervised neural operator training.

Experimental setup

Builds on: meta pseudo labels

Closest papers by meaning

• Semi-Supervised Regression with Heteroscedastic Pseudo-Labels (NeurIPS 2025 · similarity 0.89)
• Dynamic Pseudo Labeling via Gradient Cutting for High-Low Entropy Exploration (CVPR 2025 · similarity 0.87)
• High-Dimensional Bayesian Optimization via Semi-Supervised Learning with Optimized Unlabeled Data Sampling (ICML 2024 · similarity 0.86)
• Non-Stationary Predictions May Be More Informative: Exploring Pseudo-Labels with a Two-Phase Pattern of Training Dynamics (ICML 2025 · similarity 0.86)
• Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning (NeurIPS 2025 · similarity 0.86)
• Learning from Noisy Labels via Conditional Distributionally Robust Optimization (NeurIPS 2024 · similarity 0.86)