Imagen de Portada

Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Minghui, Jiang, Meirui, Zhang, Xin, Dou, Qi, Wang, Zehua, Li, Xiaoxiao
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A Closer Look at Personalized Fine-Tuning in Heterogeneous Federated Learning
por: Chen, Minghui, et al.
Publicado: (2025)

Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation
por: Xie, Guofu, et al.
Publicado: (2025)

Research in Collaborative Learning Does Not Serve Cross-Silo Federated Learning in Practice
por: Kuo, Kevin, et al.
Publicado: (2025)

Forgettable Federated Linear Learning with Certified Data Unlearning
por: Jin, Ruinan, et al.
Publicado: (2023)

FedMerge: Federated Personalization via Model Merging
por: Chen, Shutong, et al.
Publicado: (2025)

FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learning
por: Yao, Yuan, et al.
Publicado: (2025)

How to Collaborate: Towards Maximizing the Generalization Performance in Cross-Silo Federated Learning
por: Sun, Yuchang, et al.
Publicado: (2024)

PLayer-FL: A Principled Approach to Personalized Layer-wise Cross-Silo Federated Learning
por: Elhussein, Ahmed, et al.
Publicado: (2025)

Free-Rider and Conflict Aware Collaboration Formation for Cross-Silo Federated Learning
por: Chen, Mengmeng, et al.
Publicado: (2024)

Can Textual Gradient Work in Federated Learning?
por: Chen, Minghui, et al.
Publicado: (2025)

Client-Level Differential Privacy via Adaptive Intermediary in Federated Medical Imaging
por: Jiang, Meirui, et al.
Publicado: (2023)

Cross-Silo Federated Learning for Multi-Tier Networks with Vertical and Horizontal Data Partitioning
por: Das, Anirban, et al.
Publicado: (2021)

Diffusion Soup: Model Merging for Text-to-Image Diffusion Models
por: Biggs, Benjamin, et al.
Publicado: (2024)

LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks
por: Prabhakar, Akshara, et al.
Publicado: (2024)

Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
por: Zhang, Tianyi, et al.
Publicado: (2024)

Contrastive Federated Learning with Tabular Data Silos
por: Ginanjar, Achmad, et al.
Publicado: (2024)

Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy
por: Li, Tao, et al.
Publicado: (2024)

Privacy Preserving and Robust Aggregation for Cross-Silo Federated Learning in Non-IID Settings
por: Arazzi, Marco, et al.
Publicado: (2025)

FL-APU: A Software Architecture to Ease Practical Implementation of Cross-Silo Federated Learning
por: Stricker, F., et al.
Publicado: (2025)

Model Merging in the Essential Subspace
por: Li, Longhua, et al.
Publicado: (2026)

Overcoming Data and Model Heterogeneities in Decentralized Federated Learning via Synthetic Anchors
por: Huang, Chun-Yin, et al.
Publicado: (2024)

Toward Reproducible Cross-Backend Compatibility for Deep Learning: A Configuration-First Framework with Three-Tier Verification
por: Li, Zehua
Publicado: (2025)

Graph Learning Across Data Silos
por: Zhang, Xiang, et al.
Publicado: (2023)

ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy
por: Kato, Fumiyuki, et al.
Publicado: (2023)

Cross-Silo Federated Learning Across Divergent Domains with Iterative Parameter Alignment
por: Gorbett, Matt, et al.
Publicado: (2023)

Communication-Efficient Personalized Adaptation via Federated-Local Model Merging
por: Zou, Yinan, et al.
Publicado: (2026)

FedRDMA: Communication-Efficient Cross-Silo Federated LLM via Chunked RDMA Transmission
por: Zhang, Zeling, et al.
Publicado: (2024)

Expert Merging: Model Merging with Unsupervised Expert Alignment and Importance-Guided Layer Chunking
por: Zhang, Dengming, et al.
Publicado: (2025)

FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices using a Computing Power Aware Scheduler
por: Li, Zilinghan, et al.
Publicado: (2023)

Federated Learning on Virtual Heterogeneous Data with Local-global Distillation
por: Huang, Chun-Yin, et al.
Publicado: (2023)

LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups
por: Aminbeidokhti, Masih, et al.
Publicado: (2025)

SoK: Verifiable Cross-Silo FL
por: Korneev, Aleksei, et al.
Publicado: (2024)

CALM: Consensus-Aware Localized Merging for Multi-Task Learning
por: Yan, Kunda, et al.
Publicado: (2025)

Self-Soupervision: Cooking Model Soups without Labels
por: Fuller, Anthony, et al.
Publicado: (2026)

Multi-Level Collaboration in Model Merging
por: Li, Qi, et al.
Publicado: (2025)

SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHF
por: Chegini, Atoosa, et al.
Publicado: (2024)

DeFRiS: Silo-Cooperative IoT Applications Scheduling via Decentralized Federated Reinforcement Learning
por: Wang, Zhiyu, et al.
Publicado: (2026)

Disentangle Estimation of Causal Effects from Cross-Silo Data
por: Liu, Yuxuan, et al.
Publicado: (2024)

Enhanced Soups for Graph Neural Networks
por: Zuber, Joseph, et al.
Publicado: (2025)

MAGIC: Achieving Superior Model Merging via Magnitude Calibration
por: Li, Yayuan, et al.
Publicado: (2025)