Image de couverture de livre

Unlabeled Data vs. Pre-trained Knowledge: Rethinking SSL in the Era of Large Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lv, Song-Lin, Zhu, Rui, Wei, Tong, Li, Yu-Feng, Guo, Lan-Zhe
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ProtoSSL: Interpretable Prototype Learning from Unlabeled Time-Series Data
par: Song, Steven, et autres
Publié: (2026)

On Leveraging Unlabeled Data for Concurrent Positive-Unlabeled Classification and Robust Generation
par: Yu, Bing, et autres
Publié: (2020)

Designing Pre-training Datasets from Unlabeled Data for EEG Classification with Transformers
par: Bary, Tim, et autres
Publié: (2024)

PUAL: A Classifier on Trifurcate Positive-Unlabeled Data
par: Wang, Xiaoke, et autres
Publié: (2024)

Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model
par: Shi, Jiang-Xin, et autres
Publié: (2024)

Improving Full Waveform Inversion in Large Model Era
par: Feng, Yinan, et autres
Publié: (2026)

InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning
par: Huang, Zhe, et autres
Publié: (2024)

AOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training
par: Lv, Qitan, et autres
Publié: (2026)

Fine-Tuning Pre-trained Large Time Series Models for Prediction of Wind Turbine SCADA Data
par: Fan, Yuwei, et autres
Publié: (2024)

LAUD: Integrating Large Language Models with Active Learning for Unlabeled Data
par: Chou, Tzu-Hsuan, et autres
Publié: (2025)

Contrast-Aware Calibration for Fine-Tuned CLIP: Leveraging Image-Text Alignment
par: Lv, Song-Lin, et autres
Publié: (2025)

Temporal Reasoning with Large Language Models Augmented by Evolving Knowledge Graphs
par: Lin, Junhong, et autres
Publié: (2025)

Rethinking Interpretability in the Era of Large Language Models
par: Singh, Chandan, et autres
Publié: (2024)

Collaborative Unlabeled Data Optimization
par: Shang, Xinyi, et autres
Publié: (2025)

Efficient Knowledge Probing of Large Language Models by Adapting Pre-trained Embeddings
par: Sharma, Kartik, et autres
Publié: (2025)

VCC-INFUSE: Towards Accurate and Efficient Selection of Unlabeled Examples in Semi-supervised Learning
par: Fang, Shijie, et autres
Publié: (2024)

A Pre-trained Data Deduplication Model based on Active Learning
par: Shi, Haochen, et autres
Publié: (2023)

Reasoning of Large Language Models over Knowledge Graphs with Super-Relations
par: Wang, Song, et autres
Publié: (2025)

Learning from Uncertain Similarity and Unlabeled Data
par: Wei, Meng, et autres
Publié: (2025)

Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models
par: Wei, Yongxian, et autres
Publié: (2024)

SSL-SE-EEG: A Framework for Robust Learning from Unlabeled EEG Data with Self-Supervised Learning and Squeeze-Excitation Networks
par: Chowdhury, Meghna Roy, et autres
Publié: (2025)

Fractional Denoising for 3D Molecular Pre-training
par: Feng, Shikun, et autres
Publié: (2023)

PLMTrajRec: A Scalable and Generalizable Trajectory Recovery Method with Pre-trained Language Models
par: Wei, Tonglong, et autres
Publié: (2024)

TrajMamba: An Efficient and Semantic-rich Vehicle Trajectory Pre-training Model
par: Liu, Yichen, et autres
Publié: (2025)

M-Loss: Quantifying Model Merging Compatibility with Limited Unlabeled Data
par: Wang, Tiantong, et autres
Publié: (2026)

Fully Test-time Adaptation for Tabular Data
par: Zhou, Zhi, et autres
Publié: (2024)

Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers
par: Li, Xianhang, et autres
Publié: (2025)

Vision-Language Model Selection and Reuse for Downstream Adaptation
par: Tan, Hao-Zhe, et autres
Publié: (2025)

SeisMoLLM: Advancing Seismic Monitoring via Cross-modal Transfer with Pre-trained Large Language Model
par: Wang, Xinghao, et autres
Publié: (2025)

Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data
par: Zhang, Jiahan, et autres
Publié: (2024)

UNIFORM: Unifying Knowledge from Large-scale and Diverse Pre-trained Models
par: Wang, Yimu, et autres
Publié: (2025)

Re-Evaluating the Impact of Unseen-Class Unlabeled Data on Semi-Supervised Learning Model
par: He, Rundong, et autres
Publié: (2025)

Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models
par: Lai, Zhengfeng, et autres
Publié: (2024)

Decouple then Converge: Handling Unknown Unlabeled Distributions in Long-Tailed Semi-Supervised Learning
par: Gan, Kai, et autres
Publié: (2024)

Deep Positive-Unlabeled Anomaly Detection for Contaminated Unlabeled Data
par: Takahashi, Hiroshi, et autres
Publié: (2024)

Model Merging in Pre-training of Large Language Models
par: Li, Yunshui, et autres
Publié: (2025)

BMIP: Bi-directional Modality Interaction Prompt Learning for VLM
par: Lv, Song-Lin, et autres
Publié: (2025)

UniTE: A Survey and Unified Pipeline for Pre-training Spatiotemporal Trajectory Embeddings
par: Lin, Yan, et autres
Publié: (2024)

Rethinking Pre-Training in Tabular Data: A Neighborhood Embedding Perspective
par: Ye, Han-Jia, et autres
Publié: (2023)

Diffusion Domain Expansion: Learning to Coordinate Pre-trained Diffusion Models
par: Lifar, Egor, et autres
Publié: (2026)