Semi-Supervised Learning

Unlocking Partial-Label Learning: A new study reveals surprisingly simple design principles for highly accurate algorithms, dramatically simplifying future research and boosting performance.

This paper introduces a novel method for evaluating weakly supervised models using Fréchet bounds, providing reliable performance bounds without ground truth labels.

PSPS: a novel task-agnostic framework enables valid and efficient ML-assisted statistical inference for virtually any task, simply using summary statistics from existing analysis routines!

SpeAr: A novel spectral approach significantly improves zero-shot node classification by using inherent graph structure to reduce prediction bias and effectively identifying unseen node classes.

SNAPS: a novel algorithm boosts graph neural network accuracy by efficiently aggregating non-conformity scores, improving prediction sets without sacrificing validity.

This study proves that combining labeled and unlabeled data significantly improves high-dimensional sparse Gaussian classification, offering a polynomial-time SSL algorithm that outperforms supervised…

S2ML2-BBAM: A new semi-supervised multi-label learning method that balances feature angle distributions to improve accuracy and fairness.

DANCE, a novel semi-supervised framework, efficiently transfers cell types across multi-omic single-cell data even with limited labeled samples, outperforming current state-of-the-art methods.

S-MolSearch: a novel semi-supervised framework using 3D molecular data and contrastive learning achieves state-of-the-art in bioactive molecule search, outperforming existing methods.

GRASP: A novel graph augmentation strategy boosts OOD node detection by strategically adding edges to enhance the intra-edge ratio, addressing score propagation’s limitations in various scenarios.

Reinforcement Learning guides a novel semi-supervised learning method, improving model performance by adaptively balancing labeled and unlabeled data.

RankUp: Revolutionizing semi-supervised regression by cleverly adapting classification techniques for superior performance!

Persistence Homology Distillation (PsHD) leverages topological data analysis to robustly preserve structural information in semi-supervised continual learning, significantly outperforming existing met…

Colander: a novel auto-labeling technique boosts data efficiency by 60%, optimizing confidence functions for maximum coverage with minimal error.

OwMatch: a novel framework conquering open-world semi-supervised learning challenges by combining conditional self-labeling and consistency for substantially enhanced accuracy across known and unknown…

MIPLMA, a novel algorithm, enhances multi-instance partial-label learning by dynamically adjusting margins for attention scores and predicted probabilities, leading to superior performance.

Learning latent causal structures improves label noise modeling by accurately estimating noise transition matrices without relying on similarity-based assumptions, leading to state-of-the-art classifi…

Learn on massive graphs efficiently using Intersecting Community Graphs (ICGs)! This method approximates large graphs with ICGs, enabling linear time/memory complexity for node classification.

This paper introduces AdaptCDRP, a novel algorithm that uses conditional distributionally robust optimization to build robust classifiers from noisy labels, achieving superior accuracy.

Ignorance is bliss: A new framework shows ignoring label noise in multi-class classification can achieve state-of-the-art performance, especially when using self-supervised feature extraction.