English
Related papers

Related papers: Coarsening the Granularity: Towards Structurally S…

200 papers

Large-scale pre-training has recently revolutionized vision-and-language (VL) research. Models such as LXMERT and UNITER have significantly lifted the state of the art over a wide range of VL tasks. However, the large number of parameters…

Computer Vision and Pattern Recognition · Computer Science 2021-12-16 Zhe Gan , Yen-Chun Chen , Linjie Li , Tianlong Chen , Yu Cheng , Shuohang Wang , Jingjing Liu , Lijuan Wang , Zicheng Liu

Current state-of-the-art results in Music Information Retrieval are largely dominated by deep learning approaches. These provide unprecedented accuracy across all tasks. However, the consistently overlooked downside of these models is their…

Machine Learning · Computer Science 2020-08-03 Philippe Esling , Theis Bazin , Adrien Bitton , Tristan Carsault , Ninon Devis

Large Transformer-based models were shown to be reducible to a smaller number of self-attention heads and layers. We consider this phenomenon from the perspective of the lottery ticket hypothesis, using both structured and magnitude…

Computation and Language · Computer Science 2020-10-27 Sai Prasanna , Anna Rogers , Anna Rumshisky

Neural architecture search (NAS) has demonstrated amazing success in searching for efficient deep neural networks (DNNs) from a given supernet. In parallel, the lottery ticket hypothesis has shown that DNNs contain small subnetworks that…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Haoran You , Baopu Li , Zhanyi Sun , Xu Ouyang , Yingyan Celine Lin

The great success of deep neural networks is built upon their over-parameterization, which smooths the optimization landscape without degrading the generalization ability. Despite the benefits of over-parameterization, a huge amount of…

Machine Learning · Computer Science 2022-04-22 Yanwei Fu , Chen Liu , Donghao Li , Zuyuan Zhong , Xinwei Sun , Jinshan Zeng , Yuan Yao

Few-shot learning for neural networks (NNs) is an important problem that aims to train NNs with a few data. The main challenge is how to avoid overfitting since over-parameterized NNs can easily overfit to such small dataset. Previous work…

Machine Learning · Computer Science 2023-02-10 Daiki Chijiwa , Shin'ya Yamaguchi , Atsutoshi Kumagai , Yasutoshi Ida

Structural pruning enhances hardware-agnostic inference efficiency for large language models (LLMs) yet often fails to maintain comparable performance. Local pruning performs efficient layer-by-layer compression but ignores global topology.…

Machine Learning · Computer Science 2025-10-22 Guanchen Li , Yixing Xu , Zeping Li , Ji Liu , Xuanwu Yin , Dong Li , Emad Barsoum

Iterative Magnitude Pruning (IMP) is a network pruning method that repeats the process of removing weights with the least magnitudes and retraining the model. When visualizing the weight matrices of language models pruned by IMP, previous…

Computation and Language · Computer Science 2021-09-21 Dongjun Park , Geung-Hee Lee

Recent advances in neural network pruning have shown how it is possible to reduce the computational costs and memory demands of deep learning models before training. We focus on this framework and propose a new pruning at initialization…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Leonardo Iurada , Marco Ciccone , Tatiana Tommasi

Recent work has shown that renormalisation group theory is a useful framework with which to describe the process of pruning neural networks via iterative magnitude pruning. This report formally describes the link between RG theory and IMP…

Machine Learning · Computer Science 2023-06-19 Edward Prideaux-Ghee

Recent advances in artificial intelligence have relied heavily on increasingly large neural networks, raising concerns about their computational and environmental costs. This paper investigates whether simpler, sparser networks can maintain…

Machine Learning · Computer Science 2025-11-04 C. Díaz-Faloh , R. Mulet

Ensembling is a popular method used to improve performance as a last resort. However, ensembling multiple models finetuned from a single pretrained model has been not very effective; this could be due to the lack of diversity among ensemble…

Machine Learning · Computer Science 2022-05-25 Sosuke Kobayashi , Shun Kiyono , Jun Suzuki , Kentaro Inui

Network pruning has been known to produce compact models without much accuracy degradation. However, how the pruning process affects a network's robustness and the working mechanism behind remain unresolved. In this work, we theoretically…

Machine Learning · Computer Science 2022-07-13 Shufan Wang , Ningyi Liao , Liyao Xiang , Nanyang Ye , Quanshi Zhang

Since its use in the Lottery Ticket Hypothesis, iterative magnitude pruning (IMP) has become a popular method for extracting sparse subnetworks that can be trained to high performance. Despite its success, the mechanism that drives the…

Machine Learning · Computer Science 2025-10-02 William T. Redman , Zhangyang Wang , Alessandro Ingrosso , Sebastian Goldt

Graph Lottery Ticket (GLT), a combination of core subgraph and sparse subnetwork, has been proposed to mitigate the computational cost of deep Graph Neural Networks (GNNs) on large input graphs while preserving original performance.…

Machine Learning · Computer Science 2023-08-14 Yuwen Wang , Shunyu Liu , Kaixuan Chen , Tongtian Zhu , Ji Qiao , Mengjie Shi , Yuanyu Wan , Mingli Song

Many applications require sparse neural networks due to space or inference time restrictions. There is a large body of work on training dense networks to yield sparse networks for inference, but this limits the size of the largest trainable…

Machine Learning · Computer Science 2021-07-26 Utku Evci , Trevor Gale , Jacob Menick , Pablo Samuel Castro , Erich Elsen

Works on lottery ticket hypothesis (LTH) and single-shot network pruning (SNIP) have raised a lot of attention currently on post-training pruning (iterative magnitude pruning), and before-training pruning (pruning at initialization). The…

Deep Neural Networks (DNNs) are well-known to act as over-parameterized deep image priors (DIP) that regularize various image inverse problems. Meanwhile, researchers also proposed extremely compact, under-parameterized image priors (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Qiming Wu , Xiaohan Chen , Yifan Jiang , Zhangyang Wang

In this paper, we explore the performance of different pruning methods in the context of the lottery ticket hypothesis. We compare the performance of L1 unstructured pruning, Fisher pruning, and random pruning on different network…

Machine Learning · Computer Science 2023-03-29 Eirik Fladmark , Muhammad Hamza Sajjad , Laura Brinkholm Justesen

Recently, Diffenderfer and Kailkhura proposed a new paradigm for learning compact yet highly accurate binary neural networks simply by pruning and quantizing randomly weighted full precision neural networks. However, the accuracy of these…

Machine Learning · Computer Science 2022-09-27 Hao Cheng , Pu Zhao , Yize Li , Xue Lin , James Diffenderfer , Ryan Goldhahn , Bhavya Kailkhura