Buchumschlag

Ten Challenging Problems in Federated Foundation Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Fan, Tao, Gu, Hanlin, Cao, Xuemei, Chan, Chee Seng, Chen, Qian, Chen, Yiqiang, Feng, Yihui, Gu, Yang, Geng, Jiaxiang, Luo, Bing, Liu, Shuoling, Ong, Win Kent, Ren, Chao, Shao, Jiaqi, Sun, Chuan, Tang, Xiaoli, Tae, Hong Xi, Tong, Yongxin, Wei, Shuyue, Wu, Fan, Xi, Wei, Xu, Mingcong, Yang, He, Yang, Xin, Yan, Jiangpeng, Yu, Hao, Yu, Han, Zhang, Teng, Zhang, Yifei, Zhang, Xiaojin, Zheng, Zhenzhe, Fan, Lixin, Yang, Qiang
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Machine Learning Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity
von: Gu, Hanlin, et al.
Veröffentlicht: (2024)

Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosure
von: Gu, Hanlin, et al.
Veröffentlicht: (2024)

Grounding Foundation Models through Federated Transfer Learning: A General Framework
von: Kang, Yan, et al.
Veröffentlicht: (2023)

Large-Small Model Collaborative Framework for Federated Continual Learning
von: Yu, Hao, et al.
Veröffentlicht: (2025)

Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor
von: Yu, Hao, et al.
Veröffentlicht: (2024)

Disentangling data distribution for Federated Learning
von: Zhao, Xinyuan, et al.
Veröffentlicht: (2024)

FedGRPO: Privately Optimizing Foundation Models with Group-Relative Rewards from Domain Client
von: Zhu, Gongxi, et al.
Veröffentlicht: (2026)

Federated Co-tuning Framework for Large and Small Language Models
von: Fan, Tao, et al.
Veröffentlicht: (2024)

A Meta-learning Framework for Tuning Parameters of Protection Mechanisms in Trustworthy Federated Learning
von: Zhang, Xiaojin, et al.
Veröffentlicht: (2023)

A Unified Learn-to-Distort-Data Framework for Privacy-Utility Trade-off in Trustworthy Federated Learning
von: Zhang, Xiaojin, et al.
Veröffentlicht: (2024)

Deciphering the Interplay between Attack and Protection Complexity in Privacy-Preserving Federated Learning
von: Zhang, Xiaojin, et al.
Veröffentlicht: (2025)

Unlearning during Learning: An Efficient Federated Machine Unlearning Method
von: Gu, Hanlin, et al.
Veröffentlicht: (2024)

Egocentric Visibility-Aware Human Pose Estimation
von: Dai, Peng, et al.
Veröffentlicht: (2026)

FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Model
von: Shao, Shuo, et al.
Veröffentlicht: (2022)

Simplified Cofactor Conditions for Cubic to Tetragonal, Orthorhombic, and Monoclinic Phase Transformations
von: Gu, Hanlin, et al.
Veröffentlicht: (2025)

No Free Lunch Theorem for Privacy-Preserving LLM Inference
von: Zhang, Xiaojin, et al.
Veröffentlicht: (2024)

A Game-theoretic Framework for Privacy-preserving Federated Learning
von: Zhang, Xiaojin, et al.
Veröffentlicht: (2023)

A Framework for Evaluating Privacy-Utility Trade-off in Vertical Federated Learning
von: Kang, Yan, et al.
Veröffentlicht: (2022)

FedCoT: Federated Chain-of-Thought Distillation for Large Language Models
von: Fan, Tao, et al.
Veröffentlicht: (2024)

FedMKT: Federated Mutual Knowledge Transfer for Large and Small Language Models
von: Fan, Tao, et al.
Veröffentlicht: (2024)

FedEM: A Privacy-Preserving Framework for Concurrent Utility Preservation in Federated Learning
von: Xu, Mingcong, et al.
Veröffentlicht: (2025)

A Theoretical Analysis of Efficiency Constrained Utility-Privacy Bi-Objective Optimization in Federated Learning
von: Gu, Hanlin, et al.
Veröffentlicht: (2023)

CN-Buzz2Portfolio: A Chinese-Market Dataset and Benchmark for LLM-Based Macro and Sector Asset Allocation from Daily Trending Financial News
von: Chen, Liyuan, et al.
Veröffentlicht: (2026)

FedIDM: Achieving Fast and Stable Convergence in Byzantine Federated Learning through Iterative Distribution Matching
von: Yang, He, et al.
Veröffentlicht: (2026)

Hyperparameter Optimization for SecureBoost via Constrained Multi-Objective Federated Learning
von: Kang, Yan, et al.
Veröffentlicht: (2024)

Motion Primitives Planning For Center-Articulated Vehicles
von: Hu, Jiangpeng, et al.
Veröffentlicht: (2024)

Auto-Augmentation Contrastive Learning for Wearable-based Human Activity Recognition
von: Wu, Qingyu, et al.
Veröffentlicht: (2026)

FedAdOb: Privacy-Preserving Federated Deep Learning with Adaptive Obfuscation
von: Gu, Hanlin, et al.
Veröffentlicht: (2024)

Self‐Efficacy Mediates the Relationship Between Organisational Support and Health Education Competency: A Cross‐Sectional Study Among 9182 Nurses
von: Yu Mi, et al.
Veröffentlicht: (2025)

P‐N Series Integrated Ionic Thermoelectric Generator Based on Cation/Anion‐Selective Hydrogels for Body Heat Harvesting
von: Jiafu Shen, et al.
Veröffentlicht: (2025)

SyncTrack: Rhythmic Stability and Synchronization in Multi-Track Music Generation
von: Wang, Hongrui, et al.
Veröffentlicht: (2026)

Repurposing Hetrombopag for Multiple Myeloma by Targeting PNPO: A Celastrol‐Inspired Approach
von: Tianyi Yu, et al.
Veröffentlicht: (2026)

FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning
von: Zhu, Gongxi, et al.
Veröffentlicht: (2024)

InkDrop: Invisible Backdoor Attacks Against Dataset Condensation
von: Yang, He, et al.
Veröffentlicht: (2026)

Residual Stress Characterization and Microstructure Evolution Analysis of Additively Manufactured IN718 Superalloy
von: Cong Li, et al.
Veröffentlicht: (2025)

Generic Method for Integrating Lindblad Master Equations
von: Gu, Jiayin, et al.
Veröffentlicht: (2024)

Upper Bounded Current Fluctuations in One-Dimensional Driven Transport Systems
von: Gu, Jiayin, et al.
Veröffentlicht: (2024)

ErrorEraser: Unlearning Data Bias for Improved Continual Learning
von: Cao, Xuemei, et al.
Veröffentlicht: (2025)

Integrating Traditional Wisdom With Modern Science: Ginsenosides as Antiheart Failure Agents
von: Li Zhou, et al.
Veröffentlicht: (2026)

Data‐Driven Prediction of Reactivity and Additive Selection for C(sp 2 )–(Hetero)Atom Bond Couplings in an Adaptive Dynamic Homogeneous Catalysis
von: Li‐Yang Fan, et al.
Veröffentlicht: (2025)