Copertina

Partial Knowledge Distillation for Alleviating the Inherent Inter-Class Discrepancy in Federated Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Gan, Xiaoyu, Jiang, Jingbo, Zhu, Jingyang, Wang, Xiaomeng, Chen, Xizi, Tsui, Chi-Ying
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Tight Compression: Compressing CNN Through Fine-Grained Pruning and Weight Permutation for Efficient Implementation
di: Chen, Xizi, et al.
Pubblicazione: (2021)

Accelerating Large Kernel Convolutions with Nested Winograd Transformation.pdf
di: Jiang, Jingbo, et al.
Pubblicazione: (2021)

SFedKD: Sequential Federated Learning with Discrepancy-Aware Multi-Teacher Knowledge Distillation
di: Xu, Haotian, et al.
Pubblicazione: (2025)

FedLAM: Low-latency Wireless Federated Learning via Layer-wise Adaptive Modulation
di: Qu, Linping, et al.
Pubblicazione: (2025)

Federated Class-Incremental Learning with New-Class Augmented Self-Distillation
di: Wu, Zhiyuan, et al.
Pubblicazione: (2024)

How Robust is Federated Learning to Communication Error? A Comparison Study Between Uplink and Downlink Channels
di: Qu, Linping, et al.
Pubblicazione: (2023)

Optimizing Federated Graph Learning with Inherent Structural Knowledge and Dual-Densely Connected GNNs
di: Wang, Longwen, et al.
Pubblicazione: (2024)

Knowledge Distillation in Federated Edge Learning: A Survey
di: Wu, Zhiyuan, et al.
Pubblicazione: (2023)

Energy-Efficient Channel Decoding for Wireless Federated Learning: Convergence Analysis and Adaptive Design
di: Qu, Linping, et al.
Pubblicazione: (2024)

FedAQ: Communication-Efficient Federated Edge Learning via Joint Uplink and Downlink Adaptive Quantization
di: Qu, Linping, et al.
Pubblicazione: (2024)

PID-Guided Partial Alignment for Multimodal Decentralized Federated Learning
di: Shi, Yanhang, et al.
Pubblicazione: (2026)

Tailored Federated Learning: Leveraging Direction Regulation & Knowledge Distillation
di: Tang, Huidong, et al.
Pubblicazione: (2024)

Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglement
di: Wang, Houzhe, et al.
Pubblicazione: (2026)

Knowledge Distillation for Federated Learning: a Practical Guide
di: Mora, Alessio, et al.
Pubblicazione: (2022)

Toward Student-Oriented Teacher Network Training For Knowledge Distillation
di: Dong, Chengyu, et al.
Pubblicazione: (2022)

Federated Learning with Bilateral Curation for Partially Class-Disjoint Data
di: Fan, Ziqing, et al.
Pubblicazione: (2024)

Prototype-Guided and Lightweight Adapters for Inherent Interpretation and Generalisation in Federated Learning
di: Mensah, Samuel Ofosu, et al.
Pubblicazione: (2025)

Modeling Inter-Intra Heterogeneity for Graph Federated Learning
di: Yu, Wentao, et al.
Pubblicazione: (2024)

Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator
di: Zhang, Xin, et al.
Pubblicazione: (2024)

Enriching Knowledge Distillation with Intra-Class Contrastive Learning
di: Yuan, Hua, et al.
Pubblicazione: (2025)

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

MemKD: Memory-Discrepancy Knowledge Distillation for Efficient Time Series Classification
di: Udayangani, Nilushika, et al.
Pubblicazione: (2026)

Federated Learning under Partially Class-Disjoint Data via Manifold Reshaping
di: Fan, Ziqing, et al.
Pubblicazione: (2024)

On Distilling the Displacement Knowledge for Few-Shot Class-Incremental Learning
di: Fang, Pengfei, et al.
Pubblicazione: (2024)

HFedCKD: Toward Robust Heterogeneous Federated Learning via Data-free Knowledge Distillation and Two-way Contrast
di: Zheng, Yiting, et al.
Pubblicazione: (2025)

FedBook: A Unified Federated Graph Foundation Codebook with Intra-domain and Inter-domain Knowledge Modeling
di: Wu, Zhengyu, et al.
Pubblicazione: (2025)

Randomized Neural Networks for Partial Differential Equation on Static and Evolving Surfaces
di: Sun, Jingbo, et al.
Pubblicazione: (2026)

Tackling Data Heterogeneity in Federated Learning through Knowledge Distillation with Inequitable Aggregation
di: Ma, Xing
Pubblicazione: (2025)

Reviving Stale Updates: Data-Free Knowledge Distillation for Asynchronous Federated Learning
di: Askin, Baris, et al.
Pubblicazione: (2025)

FedAPM: Federated Learning via ADMM with Partial Model Personalization
di: Zhu, Shengkun, et al.
Pubblicazione: (2025)

Fast-Convergent and Communication-Alleviated Heterogeneous Hierarchical Federated Learning in Autonomous Driving
di: Kou, Wei-Bin, et al.
Pubblicazione: (2024)

Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers
di: Ding, Yongqi, et al.
Pubblicazione: (2025)

FedCFA: Alleviating Simpson's Paradox in Model Aggregation with Counterfactual Federated Learning
di: Jiang, Zhonghua, et al.
Pubblicazione: (2024)

Clustered Federated Learning with Hierarchical Knowledge Distillation
di: Ahmad, Sabtain, et al.
Pubblicazione: (2025)

UNIDEAL: Curriculum Knowledge Distillation Federated Learning
di: Yang, Yuwen, et al.
Pubblicazione: (2023)

Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions
di: Qin, Laiqiao, et al.
Pubblicazione: (2024)

Enabling Weak Client Participation via On-device Knowledge Distillation in Heterogeneous Federated Learning
di: Lim, Jihyun, et al.
Pubblicazione: (2025)

A Novel Algorithm for Personalized Federated Learning: Knowledge Distillation with Weighted Combination Loss
di: Hu, Hengrui, et al.
Pubblicazione: (2025)

Decentralized Federated Learning by Partial Message Exchange
di: Sha, Shan, et al.
Pubblicazione: (2026)

HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning
di: Khan, Momin Ahmad, et al.
Pubblicazione: (2024)