Imagen de Portada

Difficult Examples Hurt Unsupervised Contrastive Learning: A Theoretical Perspective

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Yi-Ge, Cui, Jingyi, Li, Qiran, Wang, Yisen
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

An Augmentation Overlap Theory of Contrastive Learning
por: Zhang, Qi, et al.
Publicado: (2025)

An Inclusive Theoretical Framework of Robust Supervised Contrastive Loss against Label Noise
por: Cui, Jingyi, et al.
Publicado: (2025)

Data Shifts Hurt CoT: A Theoretical Study
por: Yin, Lang, et al.
Publicado: (2025)

Do Generated Data Always Help Contrastive Learning?
por: Wang, Yifei, et al.
Publicado: (2024)

Non-negative Contrastive Learning
por: Wang, Yifei, et al.
Publicado: (2024)

Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples
por: Gao, Chengqian, et al.
Publicado: (2025)

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness
por: Zhang, Qi, et al.
Publicado: (2024)

Bridging Contrastive Learning and Domain Adaptation: Theoretical Perspective and Practical Application
por: Quintana, Gonzalo Iñaki, et al.
Publicado: (2025)

An Augmentation-Aware Theory for Self-Supervised Contrastive Learning
por: Cui, Jingyi, et al.
Publicado: (2025)

When Correct Demonstrations Hurt: Rethinking the Role of Exemplars in In-Context Learning
por: Qiu, Chenghao, et al.
Publicado: (2026)

A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima
por: Tang, Yiming, et al.
Publicado: (2025)

Towards a Novel Perspective on Adversarial Examples Driven by Frequency
por: Zhang, Zhun, et al.
Publicado: (2024)

CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning
por: Chen, Depeng, et al.
Publicado: (2024)

Parallel BiLSTM-Transformer networks for forecasting chaotic dynamics
por: Ma, Junwen, et al.
Publicado: (2025)

Dissecting the Failure of Invariant Learning on Graphs
por: Wang, Qixun, et al.
Publicado: (2024)

DeNoise: Learning Robust Graph Representations for Unsupervised Graph-Level Anomaly Detection
por: Chen, Qingfeng, et al.
Publicado: (2025)

Can Learned Optimization Make Reinforcement Learning Less Difficult?
por: Goldie, Alexander David, et al.
Publicado: (2024)

Can In-context Learning Really Generalize to Out-of-distribution Tasks?
por: Wang, Qixun, et al.
Publicado: (2024)

On the Limits of Sparse Autoencoders: A Theoretical Framework and Reweighted Remedy
por: Cui, Jingyi, et al.
Publicado: (2025)

Revisiting Modularity Maximization for Graph Clustering: A Contrastive Learning Perspective
por: Liu, Yunfei, et al.
Publicado: (2024)

LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs
por: Li, Ang, et al.
Publicado: (2025)

G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning
por: Guo, Xiaojun, et al.
Publicado: (2025)

Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective
por: Zhao, Lei, et al.
Publicado: (2023)

The Pitfalls of Memorization: When Memorization Hurts Generalization
por: Bayat, Reza, et al.
Publicado: (2024)

Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspective
por: Ji, Qirui, et al.
Publicado: (2023)

Unsupervised Representation Learning - an Invariant Risk Minimization Perspective
por: Norman, Yotam, et al.
Publicado: (2025)

JTCSE: Joint Tensor-Modulus Constraints and Cross-Attention for Unsupervised Contrastive Learning of Sentence Embeddings
por: Zong, Tianyu, et al.
Publicado: (2025)

Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the Least
por: Joshi, Siddharth, et al.
Publicado: (2023)

Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why
por: Armandpour, Mohammadreza, et al.
Publicado: (2026)

Refinement Contrastive Learning of Cell-Gene Associations for Unsupervised Cell Type Identification
por: Peng, Liang, et al.
Publicado: (2025)

CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification
por: Yin, Nan, et al.
Publicado: (2023)

A New Type of Adversarial Examples
por: Nie, Xingyang, et al.
Publicado: (2025)

Representation Collapsing Problems in Vector Quantization
por: Zhao, Wenhao, et al.
Publicado: (2024)

Unifying Lane-Level Traffic Prediction from a Graph Structural Perspective: Benchmark and Baseline
por: Li, Shuhao, et al.
Publicado: (2024)

DN-CL: Deep Symbolic Regression against Noise via Contrastive Learning
por: Liu, Jingyi, et al.
Publicado: (2024)

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

CHGNN: A Semi-Supervised Contrastive Hypergraph Learning Network
por: Song, Yumeng, et al.
Publicado: (2023)

AI-Assisted Generation of Difficult Math Questions
por: Shah, Vedant, et al.
Publicado: (2024)

Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective
por: Zhang, Feng, et al.
Publicado: (2026)

Gradient Compression May Hurt Generalization: A Remedy by Synthetic Data Guided Sharpness Aware Minimization
por: Gu, Yujie, et al.
Publicado: (2026)