English
Related papers

Related papers: Dense Backpropagation Improves Training for Sparse…

200 papers

Sparsely-activated Mixture-of-Experts (SMoE) models offer efficient pre-training and low latency but their large parameter counts create significant memory overhead, motivating research into expert compression. Contrary to recent findings…

Machine Learning · Computer Science 2026-05-14 Mike Lasby , Ivan Lazarevich , Nish Sinnadurai , Sean Lie , Yani Ioannou , Vithursan Thangarasa

Transformer models can face practical limitations due to their high computational requirements. At the same time, such models exhibit significant activation sparsity, which can be leveraged to reduce the inference cost by converting parts…

Machine Learning · Computer Science 2024-11-13 Filip Szatkowski , Bartosz Wójcik , Mikołaj Piórczyński , Simone Scardapane

Diffusion Transformer (DiT) has demonstrated remarkable performance in text-to-image generation; however, its large parameter size results in substantial inference overhead. Existing parameter compression methods primarily focus on pruning,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Youwei Zheng , Yuxi Ren , Xin Xia , Xuefeng Xiao , Xiaohua Xie

Class-incremental learning (CIL) requires deep learning models to continuously acquire new knowledge from streaming data while preserving previously learned information. Recently, CIL based on pre-trained models (PTMs) has achieved…

Machine Learning · Computer Science 2025-06-16 Linjie Li , Zhenyu Wu , Yang Ji

The Mixture-of-Experts (MoE) architecture is a powerful technique for scaling language models, yet it often suffers from expert homogenization, where experts learn redundant functionalities, thereby limiting MoE's full potential. To address…

Machine Learning · Computer Science 2026-03-03 Jiaang Li , Haibin Chen , Langming Liu , Yujin Yuan , Yadao Wang , Yizhen Zhang , Chengting Yu , Xin Tong , Weidong Zhang , Shilei Liu , Wenbo Su , Bo Zheng

Mixture-of-Experts (MoE) has emerged as a prominent architecture for scaling model size while maintaining computational efficiency. In MoE, each token in the input sequence activates a different subset of experts determined by a routing…

Computation and Language · Computer Science 2024-11-05 Chufan Shi , Cheng Yang , Xinyu Zhu , Jiahao Wang , Taiqiang Wu , Siheng Li , Deng Cai , Yujiu Yang , Yu Meng

Masked Autoencoder~(MAE) is a prevailing self-supervised learning method that achieves promising results in model pre-training. However, when the various downstream tasks have data distributions different from the pre-training data, the…

Computer Vision and Pattern Recognition · Computer Science 2024-02-09 Zhili Liu , Kai Chen , Jianhua Han , Lanqing Hong , Hang Xu , Zhenguo Li , James T. Kwok

The traditional viewpoint on Sparse Mixture of Experts (MoE) models is that instead of training a single large expert, which is computationally expensive, we can train many small experts. The hope is that if the total parameter count of the…

Machine Learning · Computer Science 2024-09-04 Youngseog Chung , Dhruv Malik , Jeff Schneider , Yuanzhi Li , Aarti Singh

Scaling Mixture-of-Experts (MoE) training introduces systems challenges absent in dense models. Because each token activates only a subset of experts, this sparsity allows total parameters to grow much faster than per-token computation,…

Recently, mixture of experts (MoE) has become a popular paradigm for achieving the trade-off between modal capacity and efficiency of multi-modal large language models (MLLMs). Different from previous efforts, we are dedicated to exploring…

Multimedia · Computer Science 2025-02-13 Qiong Wu , Zhaoxi Ke , Yiyi Zhou , Xiaoshuai Sun , Rongrong Ji

How to reduce compute and memory requirements of neural networks (NNs) without sacrificing performance? Many recent works use sparse Mixtures of Experts (MoEs) to build resource-efficient large language models (LMs). Here we introduce…

Machine Learning · Computer Science 2023-11-22 Róbert Csordás , Kazuki Irie , Jürgen Schmidhuber

Neurons in large language models often exhibit \emph{polysemanticity}, simultaneously encoding multiple unrelated concepts and obscuring interpretability. Instead of relying on post-hoc methods, we present \textbf{MoE-X}, a…

Human education system trains one student by multiple experts. Mixture-of-experts (MoE) is a powerful sparse architecture including multiple experts. However, sparse MoE model is easy to overfit, hard to deploy, and not hardware-friendly…

Machine Learning · Computer Science 2022-10-26 Fuzhao Xue , Xiaoxin He , Xiaozhe Ren , Yuxuan Lou , Yang You

Building mixture-of-experts (MoE) architecture for Low-rank adaptation (LoRA) is emerging as a potential direction in parameter-efficient fine-tuning (PEFT) for its modular design and remarkable performance. However, simply stacking the…

Machine Learning · Computer Science 2025-07-22 Jinyuan Feng , Zhiqiang Pu , Tianyi Hu , Dongmin Li , Xiaolin Ai , Huimu Wang

The Mixture-of-Experts (MoE) architecture enables a significant increase in the total number of model parameters with minimal computational overhead. However, it is not clear what performance tradeoffs, if any, exist between MoEs and…

Sparse Mixture-of-Experts (MoE) models scale Transformers efficiently but suffer from expert overlap -- redundant representations across experts and routing ambiguity, resulting in severely underutilized model capacity. While architectural…

Machine Learning · Computer Science 2026-02-17 Rizhen Hu , Yuan Cao , Boao Kong , Mou Sun , Kun Yuan

Mixture of Experts (MoE) have shown remarkable success in leveraging specialized expert networks for complex machine learning tasks. However, their susceptibility to adversarial attacks presents a critical challenge for deployment in robust…

Machine Learning · Computer Science 2025-05-28 Xu Zhang , Kaidi Xu , Ziqing Hu , Ren Wang

Transformer-based models have recently made significant advances in accurate time-series forecasting, but even these architectures struggle to scale efficiently while capturing long-term temporal dynamics. Mixture-of-Experts (MoE) layers…

Machine Learning · Computer Science 2026-03-17 Evandro S. Ortigossa , Eran Segal

Mixture of Experts (MoE), an ensemble of specialized models equipped with a router that dynamically distributes each input to appropriate experts, has achieved successful results in the field of machine learning. However, theoretical…

Machine Learning · Computer Science 2025-08-19 Ryotaro Kawata , Kohsei Matsutani , Yuri Kinoshita , Naoki Nishikawa , Taiji Suzuki

Mixture-of-Experts (MoE) models have become a key approach for scaling large language models efficiently by activating only a subset of experts during training and inference. Typically, the number of activated experts presents a trade-off:…

Machine Learning · Computer Science 2025-09-04 Yifei He , Yang Liu , Chen Liang , Hany Hassan Awadalla