English
Related papers

Related papers: Finedeep: Mitigating Sparse Activation in Dense LL…

200 papers

Mixture-of-Experts (MoE) language models can reduce computational costs by 2-4$\times$ compared to dense models without sacrificing performance, making them more efficient in computation-bounded scenarios. However, MoE models generally…

Machine Learning · Computer Science 2024-04-09 Bowen Pan , Yikang Shen , Haokun Liu , Mayank Mishra , Gaoyuan Zhang , Aude Oliva , Colin Raffel , Rameswar Panda

Deep neural networks often have millions of parameters. This can hinder their deployment to low-end devices, not only due to high memory requirements but also because of increased latency at inference. We propose a novel model compression…

Machine Learning · Computer Science 2020-06-15 Tao Lin , Sebastian U. Stich , Luis Barba , Daniil Dmitriev , Martin Jaggi

While Mixture of Experts (MoE) models achieve remarkable efficiency by activating only subsets of parameters, they suffer from high memory access costs during inference. Memory-layer architectures offer an appealing alternative with very…

Machine Learning · Computer Science 2025-08-27 Zihao Huang , Yu Bao , Qiyang Min , Siyan Chen , Ran Guo , Hongzhi Huang , Defa Zhu , Yutao Zeng , Banggu Wu , Xun Zhou , Siyuan Qiao

Large Language Models (LLMs) have demonstrated remarkable abilities in tackling a wide range of complex tasks. However, their huge computational and memory costs raise significant challenges in deploying these models on resource-constrained…

The rapid advancement of large language models (LLMs) has led to architectures with billions to trillions of parameters, posing significant deployment challenges due to their substantial demands on memory, processing power, and energy…

Machine Learning · Computer Science 2024-07-02 Enshu Liu , Junyi Zhu , Zinan Lin , Xuefei Ning , Matthew B. Blaschko , Shengen Yan , Guohao Dai , Huazhong Yang , Yu Wang

The iterations of many sparse estimation algorithms are comprised of a fixed linear filter cascaded with a thresholding nonlinearity, which collectively resemble a typical neural network layer. Consequently, a lengthy sequence of algorithm…

Machine Learning · Computer Science 2016-05-11 Bo Xin , Yizhou Wang , Wen Gao , David Wipf

Parameter-efficient fine-tuning (PEFT) is crucial for customizing Large Language Models (LLMs) with constrained resources. Although there have been various PEFT methods for dense-architecture LLMs, PEFT for sparse-architecture LLMs is still…

Computation and Language · Computer Science 2024-07-08 Zihan Wang , Deli Chen , Damai Dai , Runxin Xu , Zhuoshu Li , Y. Wu

Modern sparse language models typically achieve sparsity through Mixture-of-Experts (MoE) layers, which dynamically route tokens to dense MLP "experts." However, dynamic hard routing has a number of drawbacks, such as potentially poor…

Machine Learning · Computer Science 2026-02-02 Albert Tseng , Christopher De Sa

As large language models continue to scale, computational costs and resource consumption have emerged as significant challenges. While existing sparsification methods like pruning reduce computational overhead, they risk losing model…

Computation and Language · Computer Science 2025-09-16 Minxuan Lv , Zhenpeng Su , Leiyu Pan , Yizhe Xiong , Zijia Lin , Hui Chen , Wei Zhou , Jungong Han , Guiguang Ding , Cheng Luo , Di Zhang , Kun Gai , Songlin Hu

Machine/deep-learning (ML/DL) based techniques are emerging as a driving force behind many cutting-edge technologies, achieving high accuracy on computer vision workloads such as image classification and object detection. However, training…

Recent work has shown that directly fine-tuning large language models (LLMs) for dense retrieval yields strong performance, but their substantial parameter counts make them computationally inefficient. While prior studies have revealed…

Information Retrieval · Computer Science 2025-12-24 Yibin Lei , Shwai He , Ang Li , Andrew Yates

Fine-tuning plays a crucial role in enabling pre-trained LLMs to evolve from general language comprehension to task-specific expertise. To preserve user data privacy, federated fine-tuning is often employed and has emerged as the de facto…

Machine Learning · Computer Science 2025-03-14 Shilong Wang , Jianchun Liu , Hongli Xu , Jiaming Yan , Xianjun Gao

The performance of Transformer models has been enhanced by increasing the number of parameters and the length of the processed text. Consequently, fine-tuning the entire model becomes a memory-intensive process. High-performance methods for…

Computation and Language · Computer Science 2024-10-11 Viktoriia Chekalina , Anna Rudenko , Gleb Mezentsev , Alexander Mikhalev , Alexander Panchenko , Ivan Oseledets

The pre-training and fine-tuning paradigm has contributed to a number of breakthroughs in Natural Language Processing (NLP). Instead of directly training on a downstream task, language models are first pre-trained on large datasets with…

Machine Learning · Computer Science 2023-08-01 Vithursan Thangarasa , Abhay Gupta , William Marshall , Tianda Li , Kevin Leong , Dennis DeCoste , Sean Lie , Shreyas Saxena

Pruning has recently been widely adopted to reduce the parameter scale and improve the inference efficiency of Large Language Models (LLMs). Mainstream pruning techniques often rely on uniform layerwise pruning strategies, which can lead to…

Computation and Language · Computer Science 2025-06-04 Yuli Chen , Bo Cheng , Jiale Han , Yingying Zhang , Yingting Li , Shuhao Zhang

Recent progress of deep image classification models has provided great potential to improve state-of-the-art performance in related computer vision tasks. However, the transition to semantic segmentation is hampered by strict memory…

Computer Vision and Pattern Recognition · Computer Science 2019-05-15 Ivan Krešo , Josip Krapac , Siniša Šegvić

Sparse signal recovery problems from noisy linear measurements appear in many areas of wireless communications. In recent years, deep learning (DL) based approaches have attracted interests of researchers to solve the sparse linear inverse…

Signal Processing · Electrical Eng. & Systems 2021-01-28 Wei Chen , Bowen Zhang , Shi Jin , Bo Ai , Zhangdui Zhong

Mixture-of-Experts (MoE) layers are increasingly central to frontier model architectures. By selectively activating parameters, they reduce computational cost while scaling total parameter count. This paper investigates the impact of the…

Machine Learning · Computer Science 2025-05-13 Enric Boix-Adsera , Philippe Rigollet

Deep representation learning has become one of the most widely adopted approaches for visual search, recommendation, and identification. Retrieval of such representations from a large database is however computationally challenging.…

Machine Learning · Computer Science 2020-04-14 Biswajit Paria , Chih-Kuan Yeh , Ian E. H. Yen , Ning Xu , Pradeep Ravikumar , Barnabás Póczos

Training neural network models with discrete (categorical or structured) latent variables can be computationally challenging, due to the need for marginalization over large or combinatorial sets. To circumvent this issue, one typically…

Machine Learning · Computer Science 2020-12-29 Gonçalo M. Correia , Vlad Niculae , Wilker Aziz , André F. T. Martins