paper-with-me

홈 › Papers

MoENAS: Mixture-of-Expert based Neural Architecture Search for jointly Accurate, Fair, and Robust Edge Deep Neural Networks

2025-02-11 · Lotfi Abdelkrim Mecharbat, Alberto Marchisio, Muhammad Shafique, Mohammad M. Ghassemi, Tuka Alhanai

There has been a surge in optimizing edge Deep Neural Networks (DNNs) for accuracy and efficiency using traditional optimization techniques such as pruning, and more recently, employing automatic design methodologies. However, the focus of these design techniques has often overlooked critical metrics such as fairness, robustness, and generalization. As a result, when evaluating SOTA edge DNNs' performance in image classification using the FACET dataset, we found that they exhibit significant accuracy disparities (14.09%) across 10 different skin tones, alongside issues of non-robustness and poor generalizability. In response to these observations, we introduce Mixture-of-Experts-based Neural Architecture Search (MoENAS), an automatic design technique that navigates through a space of mixture of experts to discover accurate, fair, robust, and general edge DNNs. MoENAS improves the accuracy by 4.02% compared to SOTA edge DNNs and reduces the skin tone accuracy disparities from 14.09% to 5.60%, while enhancing robustness by 3.80% and minimizing overfitting to 0.21%, all while keeping model size close to state-of-the-art models average size (+0.4M). With these improvements, MoENAS establishes a new benchmark for edge DNN design, paving the way for the development of more inclusive and robust edge DNNs.

📄 PDF Abstract BibTeX arXiv:2502.07422

Code (0)

등록된 구현이 없습니다.

Tasks

Fairnessimage-classificationImage ClassificationMixture-of-ExpertsNeural Architecture Search

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Lifelong Mixture of Variational Autoencoders

2021-07-09 · Fei Ye, Adrian G. Bors

In this paper, we propose an end-to-end lifelong learning mixture of experts. Each expert is implemented by a Variational Autoencoder (VAE). The experts in the mixture system are jointly trained by maximizing a mixture o…

Lifelong learningMixture-of-Experts

Mixture of Weak & Strong Experts on Graphs

2023-11-09 · Hanqing Zeng, Hanjia Lyu, Diyi Hu, Yinglong Xia 외

Realistic graphs contain both (1) rich self-features of nodes and (2) informative structures of neighborhoods, jointly handled by a Graph Neural Network (GNN) in the typical setup. We propose to decouple the two modaliti…

Graph Neural NetworkNode Classification

MoQE: Improve Quantization Model performance via Mixture of Quantization Experts

2025-08-09 · Jinhao Zhang, Yunquan Zhang, Boyang Zhang, Zeyu Liu 외 arxiv

Quantization method plays a crucial role in improving model efficiency and reducing deployment costs, enabling the widespread application of deep learning models on resource-constrained devices. However, the quantization…

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…

Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning

2023-09-11 · Ted Zadouri, Ahmet Üstün, Arash Ahmadian, Beyza Ermiş 외

The Mixture of Experts (MoE) is a widely known neural architecture where an ensemble of specialized sub-models optimizes overall performance with a constant computational cost. However, conventional MoEs pose challenges …

Mixture-of-Expertsparameter-efficient fine-tuning