Copertina

UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tran, Van-Tuan, Nguyen-Le, Hong-Hanh, Ruffini, Marco, Dzaferagic, Merim
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE
di: Le, Khiem, et al.
Pubblicazione: (2025)

Modular and Integrated AI Control Framework across Fiber and Wireless Networks for 6G
di: Dzaferagic, Merim, et al.
Pubblicazione: (2025)

Bridging the High-Frequency Data Gap: A Millisecond-Resolution Network Dataset for Advancing Time Series Foundation Models
di: Khanal, Subina, et al.
Pubblicazione: (2026)

Cross-Domain AI for Early Attack Detection and Defense Against Malicious Flows in O-RAN
di: Xavier, Bruno Missi, et al.
Pubblicazione: (2024)

MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts
di: Teo, Rachel S. Y., et al.
Pubblicazione: (2024)

Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning
di: Sarkar, Soumajyoti, et al.
Pubblicazione: (2024)

ToFU: Transforming How Federated Learning Systems Forget User Data
di: Tran, Van-Tuan, et al.
Pubblicazione: (2025)

CompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competition
di: Pham, Quang, et al.
Pubblicazione: (2024)

CoSMoEs: Compact Sparse Mixture of Experts
di: Huber, Patrick, et al.
Pubblicazione: (2025)

SMoE: An Algorithm-System Co-Design for Pushing MoE to the Edge via Expert Substitution
di: Zhu, Guoying, et al.
Pubblicazione: (2025)

CompeteSMoE -- Statistically Guaranteed Mixture of Experts Training via Competition
di: Nguyen, Nam V., et al.
Pubblicazione: (2025)

ML-based handover prediction over a real O-RAN deployment using RAN Intelligent controller
di: Dzaferagic, Merim, et al.
Pubblicazione: (2024)

Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
di: Li, Pingzhi, et al.
Pubblicazione: (2023)

Demonstration of Cooperative Transport Interface over Open Source 7.2 split RAN and Virtualised Open PON Network
di: Dzaferagic, Merim, et al.
Pubblicazione: (2025)

Energy Consumption in Next Generation Radio Access Networks
di: Tariq, Urooj, et al.
Pubblicazione: (2026)

Transferable Multi-Bit Watermarking Across Frozen Diffusion Models via Latent Consistency Bridges
di: Nguyen-Le, Hong-Hanh, et al.
Pubblicazione: (2026)

Beyond Binary Classification: A Semi-supervised Approach to Generalized AI-generated Image Detection
di: Nguyen-Le, Hong-Hanh, et al.
Pubblicazione: (2025)

Passive Deepfake Detection Across Multi-modalities: A Comprehensive Survey
di: Nguyen-Le, Hong-Hanh, et al.
Pubblicazione: (2024)

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation
di: Nguyen-Le, Hong-Hanh, et al.
Pubblicazione: (2025)

D-CAPTCHA++: A Study of Resilience of Deepfake CAPTCHA under Transferable Imperceptible Adversarial Attack
di: Nguyen-Le, Hong-Hanh, et al.
Pubblicazione: (2024)

Promoting Ensemble Diversity with Interactive Bayesian Distributional Robustness for Fine-tuning Foundation Models
di: Pham, Ngoc-Quan, et al.
Pubblicazione: (2025)

Selective Sinkhorn Routing for Improved Sparse Mixture of Experts
di: Nguyen, Duc Anh, et al.
Pubblicazione: (2025)

A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts
di: Chowdhury, Mohammed Nowaz Rabbani, et al.
Pubblicazione: (2024)

Expert Merging in Sparse Mixture of Experts with Nash Bargaining
di: Nguyen, Dung V., et al.
Pubblicazione: (2025)

Demonstration of Cooperative Transport Interface using open-source 5G OpenRAN and virtualised PON network
di: Slyne, Frank, et al.
Pubblicazione: (2024)

Improving Routing in Sparse Mixture of Experts with Graph of Tokens
di: Nguyen, Tam, et al.
Pubblicazione: (2025)

On the Role of Discrete Representation in Sparse Mixture of Experts
di: Do, Giang, et al.
Pubblicazione: (2024)

Rethinking Sparse Mixture of Experts from a Unified Perspective
di: Do, Giang, et al.
Pubblicazione: (2025)

Dynamic Features Adaptation in Networking: Toward Flexible training and Explainable inference
di: Belkhiter, Yannis, et al.
Pubblicazione: (2025)

One-Prompt Strikes Back: Sparse Mixture of Experts for Prompt-based Continual Learning
di: Le, Minh, et al.
Pubblicazione: (2025)

Modeling Expert Interactions in Sparse Mixture of Experts via Graph Structures
di: Nguyen-Nhat, Minh-Khoi, et al.
Pubblicazione: (2025)

S2MoE: Robust Sparse Mixture of Experts via Stochastic Learning
di: Do, Giang, et al.
Pubblicazione: (2025)

FaaSMoE: A Serverless Framework for Multi-Tenant Mixture-of-Experts Serving
di: Wang, Minghe, et al.
Pubblicazione: (2026)

SMoA: Improving Multi-agent Large Language Models with Sparse Mixture-of-Agents
di: Li, Dawei, et al.
Pubblicazione: (2024)

RepLoRA: Reparameterizing Low-Rank Adaptation via the Perspective of Mixture of Experts
di: Truong, Tuan, et al.
Pubblicazione: (2025)

SimSMoE: Solving Representational Collapse via Similarity Measure
di: Do, Giang, et al.
Pubblicazione: (2024)

Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts
di: Wu, Jialin, et al.
Pubblicazione: (2023)

Multi-modal Adaptive Mixture of Experts for Cold-start Recommendation
di: Nguyen, Van-Khang, et al.
Pubblicazione: (2025)

On Linear Mode Connectivity of Mixture-of-Experts Architectures
di: Tran, Viet-Hoang, et al.
Pubblicazione: (2025)

FLUID: Flow-Latent Unified Integration via Token Distillation for Expert Specialization in Multimodal Learning
di: Cuong, Van Duc, et al.
Pubblicazione: (2025)