paper-with-me

Papers

Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings

2023-06-14 · Yehya Farhat, Hamza ElMokhtar Shili, Fangshuo Liao, Chen Dun, Mirian Hipolito Garcia, Guoqing Zheng, Ahmed Hassan Awadallah, Robert Sim, Dimitrios Dimitriadis, Anastasios Kyrillidis

Mixture-of-Experts (MoEs) achieve scalability by dynamically activating subsets of their components. Yet, understanding how expertise emerges through joint training of gating mechanisms and experts remains incomplete, especially in scenarios without clear task partitions. Motivated by inference costs and data heterogeneity, we study how joint training of gating functions and experts can dynamically allocate domain-specific expertise across multiple underlying data distributions. As an outcome of our framework, we develop an instance tailored specifically to decentralized training scenarios, introducing \textit{Dynamically Decentralized Orchestration of MoEs} or \texttt{DDOME}. \texttt{DDOME} leverages heterogeneity emerging from distributional shifts across decentralized data sources to specialize experts dynamically. By integrating a pretrained common expert to inform a gating function, \texttt{DDOME} achieves personalized expert subset selection on-the-fly, facilitating just-in-time personalization. We empirically validate \texttt{DDOME} within a Federated Learning (FL) context: \texttt{DDOME} attains from 4\% up to an 24\% accuracy improvement over state-of-the-art FL baselines in image and text classification tasks, while maintaining competitive zero-shot generalization capabilities. Furthermore, we provide theoretical insights confirming that the joint gating-experts training is critical for achieving meaningful expert specialization.

📄 PDF Abstract BibTeX arXiv:2306.08586

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityFederated LearningMixture-of-Expertstext-classificationText ClassificationZero-shot Generalization

Similar Papers 제목 키워드 기반

Learning to Route Among Specialized Experts for Zero-Shot Generalization

2024-02-08 · Mohammed Muqeeth, Haokun Liu, Yufan Liu, Colin Raffel

Recently, there has been a widespread proliferation of "expert" language models that are specialized to a specific task or domain through parameter-efficient fine-tuning. How can we recycle large collections of expert la…

parameter-efficient fine-tuningZero-shot Generalization

Adaptive Semantic Communication for Wireless Image Transmission Leveraging Mixture-of-Experts Mechanism

2026-04-03 · Haowen Wan, Qianqian Yang arxiv

Deep learning based semantic communication has achieved significant progress in wireless image transmission, but most existing schemes rely on fixed models and thus lack robustness to diverse image contents and dynamic c…

Semantic Communication

Domain-Specialized Object Detection via Model-Level Mixtures of Experts

2026-04-20 · Svetlana Pavlitska, Malte Stüven, Beyza Keskin, J. Marius Zöllner arxiv

Mixture-of-Experts (MoE) models provide a structured approach to combining specialized neural networks and offer greater interpretability than conventional ensembles. While MoEs have been successfully applied to image cl…

Semantic SegmentationImage ClassificationObject Detection

L-MoE: End-to-End Training of a Lightweight Mixture of Low-Rank Adaptation Experts

2025-10-19 · Shihao Ji, Zihui Song arxiv

The Mixture of Experts (MoE) architecture enables the scaling of Large Language Models (LLMs) to trillions of parameters by activating a sparse subset of weights for each input, maintaining constant computational cost du…

NavMoE: Hybrid Model- and Learning-based Traversability Estimation for Local Navigation via Mixture of Experts

2025-09-16 · Botao He, Amir Hossein Shahidzadeh, Yu Chen, Jiayi Wu 외 arxiv

This paper explores traversability estimation for robot navigation. A key bottleneck in traversability estimation lies in efficiently achieving reliable and robust predictions while accurately encoding both geometric and…

Domain GeneralizationRobot Navigation