Image de couverture de livre

Severing Spurious Correlations with Data Pruning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Mulchandani, Varun, Kim, Jung-Eun
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Trustworthy AI: Safety, Bias, and Privacy -- A Survey
par: Fang, Xingli, et autres
Publié: (2025)

Mitigating Spurious Correlations via Disagreement Probability
par: Han, Hyeonggeun, et autres
Publié: (2024)

Out of Spuriousity: Improving Robustness to Spurious Correlations without Group Annotations
par: Le, Phuong Quynh, et autres
Publié: (2024)

Spurious Correlation-Aware Embedding Regularization for Worst-Group Robustness
par: Park, Subeen, et autres
Publié: (2025)

Revisiting Spurious Correlation in Domain Generalization
par: Qin, Bin, et autres
Publié: (2024)

Combating Spurious Correlations in Graph Interpretability via Self-Reflection
par: Cai, Kecheng, et autres
Publié: (2026)

The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory
par: Tang, Luoxi, et autres
Publié: (2026)

The Pragmatic Frames of Spurious Correlations in Machine Learning: Interpreting How and Why They Matter
par: Bell, Samuel J., et autres
Publié: (2024)

Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation
par: Steinmann, David, et autres
Publié: (2024)

The Over-Certainty Phenomenon in Modern Test-Time Adaptation Algorithms
par: Amin, Fin, et autres
Publié: (2024)

Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training
par: Moya, Christian, et autres
Publié: (2026)

SCL-GNN: Towards Generalizable Graph Neural Networks via Spurious Correlation Learning
par: Zhang, Yuxiang, et autres
Publié: (2026)

Not Only the Last-Layer Features for Spurious Correlations: All Layer Deep Feature Reweighting
par: Hameed, Humza Wajid, et autres
Publié: (2024)

Identifying Spurious Correlations using Counterfactual Alignment
par: Cohen, Joseph Paul, et autres
Publié: (2023)

IPPRO: Importance-based Pruning with PRojective Offset for Magnitude-indifferent Structural Pruning
par: Jung, Jaeheun, et autres
Publié: (2025)

Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning
par: Chen, Yiwei, et autres
Publié: (2025)

Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigation
par: Liu, Chenruo, et autres
Publié: (2025)

Removing Spurious Correlation from Neural Network Interpretations
par: Fotouhi, Milad, et autres
Publié: (2024)

Measuring Sample Importance in Data Pruning for Language Models based on Information Entropy
par: Kim, Minsang, et autres
Publié: (2024)

Explaining How Quantization Disparately Skews a Model
par: Bellam, Abhimanyu, et autres
Publié: (2025)

Learnability and Privacy Vulnerability are Entangled in a Few Critical Weights
par: Fang, Xingli, et autres
Publié: (2026)

Center-Based Relaxed Learning Against Membership Inference Attacks
par: Fang, Xingli, et autres
Publié: (2024)

Decoupling Generalizability and Membership Privacy Risks in Neural Networks
par: Fang, Xingli, et autres
Publié: (2026)

Position: Retire the "Positive Backdoor" Label -- Secret Alignment Requires Strict and Systematic Evaluation
par: Li, Jianwei, et autres
Publié: (2026)

Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference
par: Li, Jianwei, et autres
Publié: (2026)

When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs
par: Wang, Shaowen, et autres
Publié: (2025)

Mitigating Spurious Correlations in NLI via LLM-Synthesized Counterfactuals and Dynamic Balanced Sampling
par: Jaimes, Christopher Román
Publié: (2025)

Spurious Rewards: Rethinking Training Signals in RLVR
par: Shao, Rulin, et autres
Publié: (2025)

Shortcut to Nowhere: Demystifying Deep Spurious Regression
par: Xu, Guanrong, et autres
Publié: (2026)

Bridging Explainability and Embeddings: BEE Aware of Spuriousness
par: Păduraru, Cristian Daniel, et autres
Publié: (2024)

Catalyst: a Novel Regularizer for Structured Pruning with Auxiliary Extension of Parameter Space
par: Jung, Jaeheun, et autres
Publié: (2025)

TopoPrune: Robust Data Pruning via Unified Latent Space Topology
par: Roy, Arjun, et autres
Publié: (2026)

Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility
par: Barsbey, Melih, et autres
Publié: (2025)

EMP: Enhance Memory in Data Pruning
par: Xiao, Jinying, et autres
Publié: (2024)

Uncovering Memorization Effect in the Presence of Spurious Correlations
par: You, Chenyu, et autres
Publié: (2025)

Safety Alignment Can Be Not Superficial With Explicit Safety Signals
par: Li, Jianwei, et autres
Publié: (2025)

RESQUE: Quantifying Estimator to Task and Distribution Shift for Sustainable Model Reusability
par: Sangarya, Vishwesh, et autres
Publié: (2024)

Multi-View Node Pruning for Accurate Graph Representation
par: Kim, Hanjin, et autres
Publié: (2025)

Data-Free Pruning of Self-Attention Layers in LLMs
par: Saikumar, Dhananjay, et autres
Publié: (2025)

Geometric Median (GM) Matching for Robust Data Pruning
par: Acharya, Anish, et autres
Publié: (2024)