Buchumschlag

Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the Least

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Joshi, Siddharth, Mirzasoleiman, Baharan
Format:	Preprint
Veröffentlicht:	2023
Schlagworte:	Machine Learning Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-Training of Deep Networks
von: Joshi, Siddharth, et al.
Veröffentlicht: (2024)

Tuning the Implicit Regularizer of Masked Diffusion Language Models: Enhancing Generalization via Insights from $k$-Parity
von: Huang, Jianhao, et al.
Veröffentlicht: (2026)

Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift
von: Xue, Yihao, et al.
Veröffentlicht: (2023)

Understanding the Role of Training Data in Test-Time Scaling
von: Javanmard, Adel, et al.
Veröffentlicht: (2025)

Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity
von: Joshi, Siddharth, et al.
Veröffentlicht: (2024)

Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models
von: Javanmard, Adel, et al.
Veröffentlicht: (2026)

Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions
von: Xue, Yihao, et al.
Veröffentlicht: (2025)

Graph Contrastive Learning under Heterophily via Graph Filters
von: Yang, Wenhan, et al.
Veröffentlicht: (2023)

Data Distribution as a Lever for Guiding Optimizers Toward Superior Generalization in LLMs
von: Gangavarapu, Tushaar, et al.
Veröffentlicht: (2026)

Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
von: Yang, Wenhan, et al.
Veröffentlicht: (2023)

How Transformers Learn to Plan via Multi-Token Prediction
von: Huang, Jianhao, et al.
Veröffentlicht: (2026)

SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models
von: Yang, Yu, et al.
Veröffentlicht: (2024)

Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization
von: Nguyen, Dang, et al.
Veröffentlicht: (2024)

Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures
von: Nguyen, Dang, et al.
Veröffentlicht: (2024)

Investigating the Benefits of Projection Head for Representation Learning
von: Xue, Yihao, et al.
Veröffentlicht: (2024)

Contrastive and Variational Approaches in Self-Supervised Learning for Complex Data Mining
von: Liang, Yingbin, et al.
Veröffentlicht: (2025)

Safe Semi-Supervised Contrastive Learning Using In-Distribution Data as Positive Examples
von: Kwak, Min Gu, et al.
Veröffentlicht: (2024)

Self-Supervised Contrastive Learning for Long-term Forecasting
von: Park, Junwoo, et al.
Veröffentlicht: (2024)

Dual Perspectives on Non-Contrastive Self-Supervised Learning
von: Ponce, Jean, et al.
Veröffentlicht: (2025)

Challenges and Opportunities in Improving Worst-Group Generalization in Presence of Spurious Features
von: Joshi, Siddharth, et al.
Veröffentlicht: (2023)

LoRA is All You Need for Safety Alignment of Reasoning LLMs
von: Xue, Yihao, et al.
Veröffentlicht: (2025)

SpeGCL: Self-supervised Graph Spectrum Contrastive Learning without Positive Samples
von: Shou, Yuntao, et al.
Veröffentlicht: (2024)

Subgraph Gaussian Embedding Contrast for Self-Supervised Graph Representation Learning
von: Xie, Shifeng, et al.
Veröffentlicht: (2025)

Rethinking Spectral Augmentation for Contrast-based Graph Self-Supervised Learning
von: Jian, Xiangru, et al.
Veröffentlicht: (2024)

Model Failure or Data Corruption? Exploring Inconsistencies in Building Energy Ratings with Self-Supervised Contrastive Learning
von: Xiao, Qian, et al.
Veröffentlicht: (2024)

Learning Label Hierarchy with Supervised Contrastive Learning
von: Lian, Ruixue, et al.
Veröffentlicht: (2024)

Deep Learning with Tabular Data: A Self-supervised Approach
von: Vyas, Tirth Kiranbhai
Veröffentlicht: (2024)

Contrastive Self-Supervised Learning As Neural Manifold Packing
von: Zhang, Guanming, et al.
Veröffentlicht: (2025)

Self-Supervised Learning for Time Series: Contrastive or Generative?
von: Liu, Ziyu, et al.
Veröffentlicht: (2024)

Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
von: Ariguib, Boshra, et al.
Veröffentlicht: (2025)

Self-supervised Graph Transformer with Contrastive Learning for Brain Connectivity Analysis towards Improving Autism Detection
von: Leng, Yicheng, et al.
Veröffentlicht: (2025)

Efficient Hierarchical Contrastive Self-supervising Learning for Time Series Classification via Importance-aware Resolution Selection
von: Garcia, Kevin, et al.
Veröffentlicht: (2025)

Difficult Examples Hurt Unsupervised Contrastive Learning: A Theoretical Perspective
von: Zhang, Yi-Ge, et al.
Veröffentlicht: (2025)

Data-Driven Self-Supervised Graph Representation Learning
von: Samy, Ahmed E., et al.
Veröffentlicht: (2024)

CellCLAT: Preserving Topology and Trimming Redundancy in Self-Supervised Cellular Contrastive Learning
von: Qin, Bin, et al.
Veröffentlicht: (2025)

Integrating Distribution Matching into Semi-Supervised Contrastive Learning for Labeled and Unlabeled Data
von: Nakayama, Shogo, et al.
Veröffentlicht: (2026)

On the Properties of Feature Attribution for Supervised Contrastive Learning
von: Arrighi, Leonardo, et al.
Veröffentlicht: (2026)

Learning Representations in Video Game Agents with Supervised Contrastive Imitation Learning
von: Celemin, Carlos, et al.
Veröffentlicht: (2025)

On the Universality of Self-Supervised Learning
von: Qiang, Wenwen, et al.
Veröffentlicht: (2024)

Self-supervised Learning Method Using Transformer for Multi-dimensional Sensor Data Processing
von: Kai, Haruki, et al.
Veröffentlicht: (2025)