↓Skip to main content

Semi-Supervised Learning

IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors
·2763 words·13 mins· loading · loading
AI Generated Machine Learning Semi-Supervised Learning 🏢 Massive Data Computing Lab, Harbin Institute of Technology
IntraMix: Boost GNN accuracy by cleverly generating high-quality labels and enriching node neighborhoods using intra-class Mixup.
Instructor-inspired Machine Learning for Robust Molecular Property Prediction
·2041 words·10 mins· loading · loading
Machine Learning Semi-Supervised Learning 🏢 Stanford University
InstructMol, a novel semi-supervised learning algorithm, leverages unlabeled data and an instructor model to significantly improve the accuracy and robustness of molecular property prediction, even wi…
Improving self-training under distribution shifts via anchored confidence with theoretical guarantees
·2507 words·12 mins· loading · loading
Machine Learning Semi-Supervised Learning 🏢 Northwestern University
Anchored Confidence (AnCon) significantly improves self-training under distribution shifts by using a temporal ensemble to smooth noisy pseudo-labels, achieving 8-16% performance gains without computa…
Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
·2869 words·14 mins· loading · loading
AI Generated Machine Learning Semi-Supervised Learning 🏢 Carnegie Mellon University
Unified framework for imprecise label learning handles noisy, partial, and semi-supervised data, improving model training efficiency and accuracy.
HGDL: Heterogeneous Graph Label Distribution Learning
·2697 words·13 mins· loading · loading
Machine Learning Semi-Supervised Learning 🏢 Florida Atlantic University
HGDL: Heterogeneous Graph Label Distribution Learning, a new framework that leverages graph topology and content to enhance label distribution prediction.
Graph Neural Networks Do Not Always Oversmooth
·1471 words·7 mins· loading · loading
Machine Learning Semi-Supervised Learning 🏢 RWTH Aachen University
Deep graph neural networks often suffer from oversmoothing; this paper reveals a non-oversmoothing phase controllable by weight variance, enabling deep, expressive models.
Generative Semi-supervised Graph Anomaly Detection
·2818 words·14 mins· loading · loading
Machine Learning Semi-Supervised Learning 🏢 School of Computing and Information Systems, Singapore Management University
GGAD: Generative Semi-supervised Graph Anomaly Detection significantly outperforms existing methods by using a novel approach to generate pseudo-anomaly nodes for training, leveraging asymmetric local…
Enhancing Semi-Supervised Learning via Representative and Diverse Sample Selection
·1698 words·8 mins· loading · loading
Machine Learning Semi-Supervised Learning 🏢 Zhejiang University
RDSS: a novel sample selection method for semi-supervised learning, boosts model accuracy by minimizing a-MMD, striking a balance between sample representativeness and diversity.
DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment
·2041 words·10 mins· loading · loading
Machine Learning Semi-Supervised Learning 🏢 Beijing Jiaotong University
DFA-GNN: A novel forward learning framework for GNNs enhances training efficiency and robustness by directly aligning feedback signals, outperforming traditional methods.
Data Augmentation with Diffusion for Open-Set Semi-Supervised Learning
·3101 words·15 mins· loading · loading
AI Generated Machine Learning Semi-Supervised Learning 🏢 Kim Jaechul Graduate School of AI, KAIST
Boosting semi-supervised learning, a new data augmentation method using diffusion models significantly improves model accuracy, especially with mismatched data distributions.
Continuous Partitioning for Graph-Based Semi-Supervised Learning
·2240 words·11 mins· loading · loading
Machine Learning Semi-Supervised Learning 🏢 UC San Diego
CutSSL: a novel framework for graph-based semi-supervised learning, surpasses state-of-the-art accuracy by solving a continuous nonconvex quadratic program that provably yields integer solutions, exce…
Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition
·2302 words·11 mins· loading · loading
Machine Learning Semi-Supervised Learning 🏢 School of Computer Science and Engineering, Southeast University
CCL, a novel probabilistic framework, uses continuous contrastive learning to excel in long-tailed semi-supervised recognition, surpassing prior state-of-the-art methods by over 4%.
Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing
·3128 words·15 mins· loading · loading
AI Generated Natural Language Processing Semi-Supervised Learning 🏢 University of Science and Technology of China
ViSu boosts semi-supervised scene text recognition by using an online generation strategy for diverse synthetic data and a novel character alignment loss to improve model generalization and robustness…
AUC Maximization under Positive Distribution Shift
·2247 words·11 mins· loading · loading
Machine Learning Semi-Supervised Learning 🏢 NTT
New method maximizes AUC under positive distribution shift using only positive and unlabeled training data, and unlabeled test data; improving imbalanced classification.
Analysis of Corrected Graph Convolutions
·1907 words·9 mins· loading · loading
AI Generated Machine Learning Semi-Supervised Learning 🏢 Cheriton School of Computer Science, University of Waterloo
Corrected graph convolutions prevent oversmoothing and exponentially improve GNN classification accuracy.