Image de couverture de livre

Improving Group Fairness in Knowledge Distillation via Laplace Approximation of Early Exits

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Fasth, Edvin, Singh, Sagar
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

Beyond Greedy Exits: Improved Early Exit Decisions for Risk Control and Reliability
par: Bajpai, Divya Jyoti, et autres
Publié: (2025)

Fair Dataset Distillation via Cross-Group Barycenter Alignment
par: Moslemi, Mohammad Hossein, et autres
Publié: (2026)

DistillSpec: Improving Speculative Decoding via Knowledge Distillation
par: Zhou, Yongchao, et autres
Publié: (2023)

S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models
par: Dai, Muzhi, et autres
Publié: (2025)

laplax -- Laplace Approximations with JAX
par: Weber, Tobias, et autres
Publié: (2025)

Improving LLM Group Fairness on Tabular Data via In-Context Learning
par: Cherepanova, Valeriia, et autres
Publié: (2024)

AEBNAS: Strengthening Exit Branches in Early-Exit Networks through Hardware-Aware Neural Architecture Search
par: Robben, Oscar, et autres
Publié: (2025)

SAFE-KD: Risk-Controlled Early-Exit Distillation for Vision Backbones
par: Khazem, Salim
Publié: (2026)

Improve Knowledge Distillation via Label Revision and Data Selection
par: Lan, Weichao, et autres
Publié: (2024)

FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning
par: Cinquin, Tristan, et autres
Publié: (2024)

Early-Exit Neural Networks with Nested Prediction Sets
par: Jazbec, Metod, et autres
Publié: (2023)

Attention Consistency Regularization for Interpretable Early-Exit Neural Networks
par: Zhao, Yanhua
Publié: (2026)

Tubular Riemannian Laplace Approximations for Bayesian Neural Networks
par: David, Rodrigo Pereira
Publié: (2025)

On the Laplace Approximation as Model Selection Criterion for Gaussian Processes
par: Besginow, Andreas, et autres
Publié: (2024)

Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exits
par: Elboher, Yizhak Yisrael, et autres
Publié: (2025)

On-Sensor Convolutional Neural Networks with Early-Exits
par: Shalby, Hazem Hesham Yousef, et autres
Publié: (2025)

Dynamic Vocabulary Pruning in Early-Exit LLMs
par: Vincenti, Jort, et autres
Publié: (2024)

Know What You Don't Know: Selective Prediction for Early Exit DNNs
par: Bajpai, Divya Jyoti, et autres
Publié: (2025)

Identity Curvature Laplace Approximation for Improved Out-of-Distribution Detection
par: Zhdanov, Maksim, et autres
Publié: (2023)

SpecExit: Accelerating Large Reasoning Model via Speculative Exit
par: Yang, Rubing, et autres
Publié: (2025)

Self-Supervised Laplace Approximation for Bayesian Uncertainty Quantification
par: Rodemann, Julian, et autres
Publié: (2026)

Temporal Decisions: Leveraging Temporal Correlation for Efficient Decisions in Early Exit Neural Networks
par: Sponner, Max, et autres
Publié: (2024)

Group Relative Knowledge Distillation: Learning from Teacher's Relational Inductive Bias
par: Li, Chao, et autres
Publié: (2025)

Logical Distillation of Graph Neural Networks
par: Pluska, Alexander, et autres
Publié: (2024)

Hetero-SplitEE: Split Learning of Neural Networks with Early Exits for Heterogeneous IoT Devices
par: Oda, Yuki, et autres
Publié: (2025)

Low-Dimensional Federated Knowledge Graph Embedding via Knowledge Distillation
par: Zhang, Xiaoxiong, et autres
Publié: (2024)

Generating Synthetic Fair Syntax-agnostic Data by Learning and Distilling Fair Representation
par: Sikder, Md Fahim, et autres
Publié: (2024)

Model Merging via Multi-Teacher Knowledge Distillation
par: Dalili, Seyed Arshan, et autres
Publié: (2025)

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
par: Elhoushi, Mostafa, et autres
Publié: (2024)

One Jump Is All You Need: Short-Cutting Transformers for Early Exit Prediction with One Jump to Fit All Exit Levels
par: Seshadri, Amrit Diggavi
Publié: (2025)

Overcoming label shift with target-aware federated learning
par: Zec, Edvin Listo, et autres
Publié: (2024)

TaxDistill: Improving Metagenomic Taxonomic Annotation via Distilled Genomic Foundation Models
par: Ye, Rongye, et autres
Publié: (2026)

Fair Recourse for All: Ensuring Individual and Group Fairness in Counterfactual Explanations
par: Ezzeddine, Fatima, et autres
Publié: (2026)

Procedural Fairness via Group Counterfactual Explanation
par: Popoola, Gideon, et autres
Publié: (2026)

DCentNet: Decentralized Multistage Biomedical Signal Classification using Early Exits
par: Li, Xiaolin, et autres
Publié: (2025)

SPARQ: Spiking Early-Exit Neural Networks for Energy-Efficient Edge AI
par: Patne, Parth, et autres
Publié: (2026)

DART: Input-Difficulty-AwaRe Adaptive Threshold for Early-Exit DNNs
par: Patne, Parth, et autres
Publié: (2026)

TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
par: Nagle, Alliot, et autres
Publié: (2026)

GLOCALFAIR: Jointly Improving Global and Local Group Fairness in Federated Learning
par: Meerza, Syed Irfan Ali, et autres
Publié: (2024)

Fair4Free: Generating High-fidelity Fair Synthetic Samples using Data Free Distillation
par: Sikder, Md Fahim, et autres
Publié: (2024)