English
Related papers

Related papers: Pruning Pretrained Encoders with a Multitask Objec…

200 papers

We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…

Computation and Language · Computer Science 2020-10-27 Hyung Won Chung , Thibault Févry , Henry Tsai , Melvin Johnson , Sebastian Ruder

Multi-encoder models are a broad family of context-aware neural machine translation systems that aim to improve translation quality by encoding document-level contextual information alongside the current sentence. The context encoding is…

Computation and Language · Computer Science 2022-10-25 Lorenzo Lupo , Marco Dinarelli , Laurent Besacier

Channel pruning is an important family of methods to speed up deep model's inference. Previous filter pruning algorithms regard channel pruning and model fine-tuning as two independent steps. This paper argues that combining them into a…

Computer Vision and Pattern Recognition · Computer Science 2019-01-18 Jian-Hao Luo , Jianxin Wu

Multimodal large language models (MLLMs) have shown remarkable performance for cross-modal understanding and generation, yet still suffer from severe inference costs. Recently, abundant works have been proposed to solve this problem with…

Computation and Language · Computer Science 2025-05-30 Zichen Wen , Yifeng Gao , Weijia Li , Conghui He , Linfeng Zhang

Model pruning has gained traction as a promising defense strategy against backdoor attacks in deep learning. However, existing pruning-based approaches often fall short in accurately identifying and removing the specific parameters…

Computer Vision and Pattern Recognition · Computer Science 2025-10-16 Kealan Dunnett , Reza Arablouei , Dimity Miller , Volkan Dedeoglu , Raja Jurdak

Pruning deep neural networks is a widely used strategy to alleviate the computational burden in machine learning. Overwhelming empirical evidence suggests that pruned models retain very high accuracy even with a tiny fraction of parameters.…

Machine Learning · Computer Science 2023-09-27 Viplove Arora , Daniele Irto , Sebastian Goldt , Guido Sanguinetti

Pretrained Transformers achieve state-of-the-art performance in various code-processing tasks but may be too large to be deployed. As software development tools often incorporate modules for various purposes which may potentially use a…

Computation and Language · Computer Science 2022-12-13 Shamil Ayupov , Nadezhda Chirkova

Deep Neural Networks(DNNs) have many parameters and activation data, and these both are expensive to implement. One method to reduce the size of the DNN is to quantize the pre-trained model by using a low-bit expression for weights and…

Computer Vision and Pattern Recognition · Computer Science 2020-11-26 Jun Nishikawa , Ryoji Ikegaya

Neural networks are increasingly used as surrogates in optimization problems to replace computationally expensive models. However, embedding ReLU neural networks in mathematical programs introduces significant computational challenges,…

Optimization and Control · Mathematics 2026-04-03 Giacomo Lastrucci , Tanuj Karia , Victor Schulte , Dominik Bongartz , Artur M. Schweidtmann

Network pruning is widely used for reducing the heavy inference cost of deep models in low-resource settings. A typical pruning algorithm is a three-stage pipeline, i.e., training (a large model), pruning and fine-tuning. During pruning,…

Machine Learning · Computer Science 2019-03-06 Zhuang Liu , Mingjie Sun , Tinghui Zhou , Gao Huang , Trevor Darrell

Large language models are versatile tools but are not suitable for small inference budgets. Small models have more efficient inference, but their lower capacity means that their performance can be good only if one limits their scope to a…

Machine Learning · Computer Science 2024-11-01 David Grangier , Angelos Katharopoulos , Pierre Ablin , Awni Hannun

Neural network pruning---the task of reducing the size of a network by removing parameters---has been the subject of a great deal of work in recent years. We provide a meta-analysis of the literature, including an overview of approaches to…

Machine Learning · Computer Science 2020-03-09 Davis Blalock , Jose Javier Gonzalez Ortiz , Jonathan Frankle , John Guttag

As neural networks grow in size and complexity, inference speeds decline. To combat this, one of the most effective compression techniques -- channel pruning -- removes channels from weights. However, for multi-branch segments of a model,…

Computer Vision and Pattern Recognition · Computer Science 2023-07-19 Alvin Wan , Hanxiang Hao , Kaushik Patnaik , Yueyang Xu , Omer Hadad , David Güera , Zhile Ren , Qi Shan

Pruning and quantization techniques have been broadly successful in reducing the number of parameters needed for large neural networks, yet theoretical justification for their empirical success falls short. We consider a randomized greedy…

Machine Learning · Computer Science 2025-12-09 Houssam El Cheairi , David Gamarnik , Rahul Mazumder

Self-supervised pre-training of large-scale transformer models on text corpora followed by finetuning has achieved state-of-the-art on a number of natural language processing tasks. Recently, Lu et al. (2021, arXiv:2103.05247) claimed that…

Machine Learning · Computer Science 2021-07-28 Danielle Rothermel , Margaret Li , Tim Rocktäschel , Jakob Foerster

This work suggests fundamentally rethinking the current practice of pruning large language models (LLMs). The way it is done is by divide and conquer: split the model into submodels, sequentially prune them, and reconstruct predictions of…

Computation and Language · Computer Science 2024-10-14 Sungbin Shin , Wonpyo Park , Jaeho Lee , Namhoon Lee

Transformer-based NLP models are trained using hundreds of millions or even billions of parameters, limiting their applicability in computationally constrained environments. While the number of parameters generally correlates with…

Computation and Language · Computer Science 2022-08-16 Hassan Sajjad , Fahim Dalvi , Nadir Durrani , Preslav Nakov

Unsupervised pre-training approaches have achieved great success in many fields such as Computer Vision (CV), Natural Language Processing (NLP) and so on. However, compared to typical deep learning models, pre-training or even fine-tuning…

Computer Vision and Pattern Recognition · Computer Science 2023-02-22 Penghao Jiang , Xuanchen Hou , Yinsi Zhou

This study explores a novel approach to neural network pruning using evolutionary computation, focusing on simultaneously pruning the encoder and decoder of an autoencoder. We introduce two new mutation operators that use layer activations…

Neural and Evolutionary Computing · Computer Science 2025-05-09 Steven Jorgensen , Erik Hemberg , Jamal Toutouh , Una-May O'Reilly

Large Language Models (LLMs) demonstrate exceptional reasoning abilities, enabling strong generalization across diverse tasks such as commonsense reasoning and instruction following. However, as LLMs scale, inference costs become…

Computation and Language · Computer Science 2025-02-06 Rhea Sanjay Sukthanker , Benedikt Staffler , Frank Hutter , Aaron Klein