English
Related papers

Related papers: Adaptive Dropout for Pruning Conformers

200 papers

Channel pruning is one of the major compression approaches for deep neural networks. While previous pruning methods have mostly focused on identifying unimportant channels, channel pruning is considered as a special case of neural…

Computer Vision and Pattern Recognition · Computer Science 2021-09-15 Xiangcheng Liu , Jian Cao , Hongyi Yao , Wenyu Sun , Yuan Zhang

Large Language Models (LLMs) have shown immense potential in enhancing various aspects of our daily lives, from conversational AI to search and AI assistants. However, their growing capabilities come at the cost of extremely large model…

Machine Learning · Computer Science 2025-02-27 Yingyu Liang , Jiangxuan Long , Zhenmei Shi , Zhao Song , Yufa Zhou

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

Deep neural networks have dramatically achieved great success on a variety of challenging tasks. However, most successful DNNs have an extremely complex structure, leading to extensive research on model compression.As a significant area of…

Machine Learning · Computer Science 2020-04-13 Haipeng Jia , Xueshuang Xiang , Da Fan , Meiyu Huang , Changhao Sun , Yang He

Large language models (LLMs) have achieved significant success across various domains. However, training these LLMs typically involves substantial memory and computational costs during both forward and backward propagation. While…

Machine Learning · Computer Science 2025-03-03 Sunghyeon Woo , Baeseong Park , Byeongwook Kim , Minjung Jo , Se Jung Kwon , Dongsuk Jeon , Dongsoo Lee

Deep neural network (DNN)-based adaptive controllers can be used to compensate for unstructured uncertainties in nonlinear dynamic systems. However, DNNs are also very susceptible to overfitting and co-adaptation. Dropout regularization is…

Systems and Control · Electrical Eng. & Systems 2023-11-01 Saiedeh Akbari , Emily J. Griffis , Omkar Sudhir Patil , Warren E. Dixon

While convolutional neural networks (CNN) have achieved impressive performance on various classification/recognition tasks, they typically consist of a massive number of parameters. This results in significant memory requirement as well as…

Computer Vision and Pattern Recognition · Computer Science 2019-05-14 Pravendra Singh , Vinay Kumar Verma , Piyush Rai , Vinay P. Namboodiri

Variants dropout methods have been designed for the fully-connected layer, convolutional layer and recurrent layer in neural networks, and shown to be effective to avoid overfitting. As an appealing alternative to recurrent and…

Computation and Language · Computer Science 2019-07-29 Lin Zehui , Pengfei Liu , Luyao Huang , Junkun Chen , Xipeng Qiu , Xuanjing Huang

The Resilient Propagation (Rprop) algorithm has been very popular for backpropagation training of multilayer feed-forward neural networks in various applications. The standard Rprop however encounters difficulties in the context of deep…

Neural and Evolutionary Computing · Computer Science 2015-09-17 Alan Mosca , George D. Magoulas

In this paper, we propose a novel method for speaker adaptation in lip reading, motivated by two observations. Firstly, a speaker's own characteristics can always be portrayed well by his/her few facial images or even a single image with…

Computer Vision and Pattern Recognition · Computer Science 2024-05-01 Songtao Luo , Shuang Yang , Shiguang Shan , Xilin Chen

Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. However, such impressive capability typically comes with a substantial model size, which presents significant challenges in deployment…

Computation and Language · Computer Science 2025-06-26 Guinan Su , Li Shen , Lu Yin , Shiwei Liu , Yanwu Yang , Jonas Geiping

Federated Learning (FL) has emerged as a new paradigm for training machine learning models distributively without sacrificing data security and privacy. Learning models on edge devices such as mobile phones is one of the most common use…

Machine Learning · Computer Science 2023-02-10 Sixing Yu , Phuong Nguyen , Ali Anwar , Ali Jannesari

Adapting pre-trained neural models to downstream tasks has become the standard practice for obtaining high-quality models. In this work, we propose a novel model adaptation paradigm, adapting by pruning, which prunes neural connections in…

Machine Learning · Computer Science 2021-05-10 Yang Gao , Nicolo Colombo , Wei Wang

The training phases of Deep neural network~(DNN) consumes enormous processing time and energy. Compression techniques utilizing the sparsity of DNNs can effectively accelerate the inference phase of DNNs. However, it can be hardly used in…

Machine Learning · Computer Science 2018-12-17 Zhuoran Song , Ru Wang , Dongyu Ru , Hongru Huang , Zhenghao Peng , Jing Ke , Xiaoyao Liang , Li Jiang

Recent studies have demonstrated that many layers are functionally redundant in large language models (LLMs), enabling model compression by removing these layers to reduce inference cost. While such approaches can improve efficiency,…

Computation and Language · Computer Science 2026-02-24 Kainan Liu , Yong Zhang , Ning Cheng , Zhitao Li , Shaojun Wang , Jing Xiao

Conventional continual pretraining (CPT) for large language model (LLM) domain adaptation often suffers from catastrophic forgetting and limited domain capacity. Existing strategies adopt layer expansion, introducing additional trainable…

Machine Learning · Computer Science 2025-10-14 Jinyang Zhang , Yue Fang , Hongxin Ding , Weibin Liao , Muyang Ye , Xu Chu , Junfeng Zhao , Yasha Wang

We propose DropMax, a stochastic version of softmax classifier which at each iteration drops non-target classes according to dropout probabilities adaptively decided for each instance. Specifically, we overlay binary masking variables over…

Machine Learning · Computer Science 2018-11-05 Hae Beom Lee , Juho Lee , Saehoon Kim , Eunho Yang , Sung Ju Hwang

Dropout is a widely used regularization technique which improves the generalization ability of a model by randomly dropping neurons. In light of this, we propose Dropout Prompt Learning, which aims for applying dropout to improve the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Biao Chen , Lin Zuo , Mengmeng Jing , Kunbin He , Yuchen Wang

The success of convolutional neural networks (CNNs) in various applications is accompanied by a significant increase in computation and parameter storage costs. Recent efforts to reduce these overheads involve pruning and compressing the…

Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency. However, conventional training-free structured pruning methods often employ a heuristic metric that…

Computation and Language · Computer Science 2026-01-28 Songtao Liu , Peng Liu