Image de couverture de livre

Same Target, Different Basins: Hard vs. Soft Labels for Annotator Distributions

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gheibi, Mirerfan, Ghazizadeh, Gashin
Format:	Preprint
Publié:	2026
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

A Theoretical Analysis of Soft-Label vs Hard-Label Training in Neural Networks
par: Mandal, Saptarshi, et autres
Publié: (2024)

Hardness, Structural Knowledge, and Opportunity: An Analytical Framework for Modular Performance Modeling
par: Gheibi, Omid, et autres
Publié: (2025)

Grokking vs. Learning: Same Features, Different Encodings
par: Manning-Coe, Dmitry, et autres
Publié: (2025)

Label Distribution Learning with Biased Annotations by Learning Multi-Label Representation
par: Kou, Zhiqiang, et autres
Publié: (2025)

The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works
par: Wang, Guanghui, et autres
Publié: (2026)

Rethinking Dataset Distillation: Hard Truths about Soft Labels
par: Dey, Priyam, et autres
Publié: (2026)

Trustworthy Federated Label Distribution Learning under Annotation Quality Disparity
par: Wu, Junxiang, et autres
Publié: (2026)

Dealing with Drift of Adaptation Spaces in Learning-based Self-Adaptive Systems using Lifelong Self-Adaptation
par: Gheibi, Omid, et autres
Publié: (2022)

An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration
par: Pavlovic, Maja, et autres
Publié: (2026)

Sparse Autoencoders Trained on the Same Data Learn Different Features
par: Paulo, Gonçalo, et autres
Publié: (2025)

Soft Label PU Learning
par: Zhao, Puning, et autres
Publié: (2024)

Label Forensics: Interpreting Hard Labels in Black-Box Text Classifier
par: Du, Mengyao, et autres
Publié: (2025)

Vocal Melody Construction for Persian Lyrics Using LSTM Recurrent Neural Networks
par: Jafari, Farshad, et autres
Publié: (2024)

Learning from Ambiguous Data with Hard Labels
par: Xie, Zeke, et autres
Publié: (2025)

Reduced Jeffries-Matusita distance: A Novel Loss Function to Improve Generalization Performance of Deep Classification Models
par: Lashkari, Mohammad, et autres
Publié: (2024)

Salutary Labeling with Zero Human Annotation
par: Xiao, Wenxiao, et autres
Publié: (2024)

Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws
par: Jha, Nandan Kumar, et autres
Publié: (2026)

Learning from Hard Labels with Additional Supervision on Non-Hard-Labeled Classes
par: Sugiyama, Kosuke, et autres
Publié: (2025)

Rethinking Self-Distillation: Label Averaging and Enhanced Soft Label Refinement with Partial Labels
par: Jeong, Hyeonsu, et autres
Publié: (2024)

Soft Tokens, Hard Truths
par: Butt, Natasha, et autres
Publié: (2025)

Accelerating Targeted Hard-Label Adversarial Attacks in Low-Query Black-Box Settings
par: Swaminathan, Arjhun, et autres
Publié: (2025)

Generating the Ground Truth: Synthetic Data for Soft Label and Label Noise Research
par: de Vries, Sjoerd, et autres
Publié: (2023)

Learning to Translate from Soft to Hard LLM Prompts
par: Kongsomjit, Pitipat, et autres
Publié: (2026)

Probabilistic Label Spreading: Efficient and Consistent Estimation of Soft Labels with Epistemic Uncertainty on Graphs
par: Klees, Jonathan, et autres
Publié: (2026)

Same Graph, Different Likelihoods: Calibration of Autoregressive Graph Generators via Permutation-Equivalent Encodings
par: Fredsgaard, Laurits, et autres
Publié: (2026)

Multi-Label Adaptive Batch Selection by Highlighting Hard and Imbalanced Samples
par: Zhou, Ao, et autres
Publié: (2024)

ActiveLab: Active Learning with Re-Labeling by Multiple Annotators
par: Goh, Hui Wen, et autres
Publié: (2023)

Hard-Label Cryptanalytic Extraction of Neural Network Models
par: Chen, Yi, et autres
Publié: (2024)

Is the Hard-Label Cryptanalytic Model Extraction Really Polynomial?
par: Ito, Akira, et autres
Publié: (2025)

Same Error, Different Function: The Optimizer as an Implicit Prior in Financial Time Series
par: Cortesi, Federico Vittorio, et autres
Publié: (2026)

Hard and Soft EM in Bayesian Network Learning from Incomplete Data
par: Ruggieri, Andrea, et autres
Publié: (2020)

Lon-ea at SemEval-2023 Task 11: A Comparison of Activation Functions for Soft and Hard Label Prediction
par: Hosseini, Peyman, et autres
Publié: (2023)

Soft-to-Hard Routing in Sparse Mixture-of-Experts Models
par: Rastegar, Reza
Publié: (2026)

Soft-Label Caching and Sharpening for Communication-Efficient Federated Distillation
par: Azuma, Kitsuya, et autres
Publié: (2025)

Learning with Confidence: Training Better Classifiers from Soft Labels
par: de Vries, Sjoerd, et autres
Publié: (2024)

Scalable Label Distribution Learning for Multi-Label Classification
par: Zhao, Xingyu, et autres
Publié: (2023)

Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMs
par: Thapaliya, Safal, et autres
Publié: (2026)

Soft-Label Training Preserves Epistemic Uncertainty
par: Singh, Agamdeep, et autres
Publié: (2025)

Structural Abstraction as an Inductive Bias for Non-Stationary Language Model Training
par: Rahmati, Elnaz, et autres
Publié: (2026)

Low-Cost Hard-Label Adversarial Attack with Theoretical Foundations
par: Liu, Jun, et autres
Publié: (2026)