Cover Image

Soft-Label Caching and Sharpening for Communication-Efficient Federated Distillation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Azuma, Kitsuya, Nishio, Takayuki, Kitagawa, Yuichi, Nakano, Wakako, Tanimura, Takahito
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

BlazeFL: Fast and Deterministic Federated Learning Simulation
by: Azuma, Kitsuya, et al.
Published: (2026)

Enabling Federated Inference via Unsupervised Consensus Embedding
by: Hashimoto, Yui, et al.
Published: (2026)

Load-Aware Training Scheduling for Model Circulation-based Decentralized Federated Learning
by: Kainuma, Haruki, et al.
Published: (2025)

Lightweight User-Personalization Method for Closed Split Computing
by: Okada, Yuya, et al.
Published: (2026)

Multi-Station WiFi CSI Sensing Framework Robust to Station-wise Feature Missingness and Limited Labeled Data
by: Kayano, Keita, et al.
Published: (2026)

Rethinking Self-Distillation: Label Averaging and Enhanced Soft Label Refinement with Partial Labels
by: Jeong, Hyeonsu, et al.
Published: (2024)

FedCache 2.0: Federated Edge Learning with Knowledge Caching and Dataset Distillation
by: Pan, Quyang, et al.
Published: (2024)

SALT: A Lightweight Model Adaptation Method for Closed Split Computing Environments
by: Okada, Yuya, et al.
Published: (2025)

Personalized Federated Distillation Assisted Vehicle Edge Caching Strategy
by: Li, Xun, et al.
Published: (2025)

Consistently Informative Soft-Label Temperature for Knowledge Distillation
by: Luong, Hoang-Chau, et al.
Published: (2026)

$Λ$-Split: A Privacy-Preserving Split Computing Framework for Cloud-Powered Generative AI
by: Ohta, Shoki, et al.
Published: (2023)

Soft Separation and Distillation: Toward Global Uniformity in Federated Unsupervised Learning
by: Fang, Hung-Chieh, et al.
Published: (2025)

The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works
by: Wang, Guanghui, et al.
Published: (2026)

Rethinking Dataset Distillation: Hard Truths about Soft Labels
by: Dey, Priyam, et al.
Published: (2026)

Probabilistic Label Spreading: Efficient and Consistent Estimation of Soft Labels with Epistemic Uncertainty on Graphs
by: Klees, Jonathan, et al.
Published: (2026)

Federated Learning with Label-Masking Distillation
by: Lu, Jianghu, et al.
Published: (2024)

Soft Label Pruning and Quantization for Large-Scale Dataset Distillation
by: Lingao, Xiao, et al.
Published: (2026)

Soft Label PU Learning
by: Zhao, Puning, et al.
Published: (2024)

Self-Consistency via Marginal Sharpening
by: Arzhantsev, Aleksei, et al.
Published: (2026)

A Minimalist Example of Edge-of-Stability and Progressive Sharpening
by: Liu, Liming, et al.
Published: (2025)

Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning
by: Gai, Jingchu, et al.
Published: (2025)

Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpening
by: He, Andre, et al.
Published: (2025)

Label Cluster Chains for Multi-Label Classification
by: Gatto, Elaine Cecília, et al.
Published: (2024)

Communication-Efficient Federated Learning through Adaptive Weight Clustering and Server-Side Distillation
by: Tsouvalas, Vasileios, et al.
Published: (2024)

Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation
by: Zhao, Shiji, et al.
Published: (2023)

Communication-Efficient Gluon in Federated Learning
by: Qian, Xun, et al.
Published: (2026)

One-shot Federated Learning via Synthetic Distiller-Distillate Communication
by: Zhang, Junyuan, et al.
Published: (2024)

KVSculpt: KV Cache Compression as Distillation
by: Jiang, Bo, et al.
Published: (2026)

Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
by: Zaz, Brown, et al.
Published: (2026)

KaVa: Latent Reasoning via Compressed KV-Cache Distillation
by: Kuzina, Anna, et al.
Published: (2025)

Beyond Distribution Sharpening: The Importance of Task Rewards
by: Mittal, Sarthak, et al.
Published: (2026)

Sharpened Lazy Incremental Quasi-Newton Method
by: Lahoti, Aakash, et al.
Published: (2023)

Generating the Ground Truth: Synthetic Data for Soft Label and Label Noise Research
by: de Vries, Sjoerd, et al.
Published: (2023)

Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening
by: Ji, Xiaotong, et al.
Published: (2026)

How to Compress KV Cache in RL Post-Training? Shadow Mask Distillation for Memory-Efficient Alignment
by: Zhu, Rui, et al.
Published: (2026)

IC-Cache: Efficient Large Language Model Serving via In-context Caching
by: Yu, Yifan, et al.
Published: (2025)

Towards Autonomous Driving of Personal Mobility with Small and Noisy Dataset using Tsallis-statistics-based Behavioral Cloning
by: Kobayashi, Taisuke, et al.
Published: (2021)

Federated UCBVI: Communication-Efficient Federated Regret Minimization with Heterogeneous Agents
by: Labbi, Safwan, et al.
Published: (2024)

Communication-Aware Knowledge Distillation for Federated LLM Fine-Tuning over Wireless Networks
by: Zhang, Xinlu, et al.
Published: (2025)

Is the Hard-Label Cryptanalytic Model Extraction Really Polynomial?
by: Ito, Akira, et al.
Published: (2025)