English
Related papers

Related papers: The Lottery Ticket Hypothesis for Self-attention i…

200 papers

The lottery ticket hypothesis (LTH) claims that a deep neural network (i.e., ground network) contains a number of subnetworks (i.e., winning tickets), each of which exhibiting identically accurate inference capability as that of the ground…

Machine Learning · Computer Science 2021-04-27 Sejin Seo , Seung-Woo Ko , Jihong Park , Seong-Lyun Kim , Mehdi Bennis

Over-parameterized neural networks incur prohibitive memory and computational costs for resource-constrained deployment. The Strong Lottery Ticket (SLT) hypothesis suggests that randomly initialized networks contain sparse subnetworks…

Machine Learning · Computer Science 2026-03-11 Itamar Tsayag , Ofir Lindenbaum

In pruning, the Lottery Ticket Hypothesis posits that large networks contain sparse subnetworks, or winning tickets, that can be trained in isolation to match the performance of their dense counterparts. However, most existing approaches…

Artificial Intelligence · Computer Science 2026-01-30 Grzegorz Stefanski , Alberto Presta , Michal Byra

Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. Many continual learning (CL) strategies are trying to overcome this problem. One of the most effective is the…

Machine Learning · Computer Science 2024-05-27 Kamil Książek , Przemysław Spurek

In deep model compression, the recent finding "Lottery Ticket Hypothesis" (LTH) (Frankle & Carbin, 2018) pointed out that there could exist a winning ticket (i.e., a properly pruned sub-network together with original weight initialization)…

Machine Learning · Computer Science 2021-07-20 Ning Liu , Geng Yuan , Zhengping Che , Xuan Shen , Xiaolong Ma , Qing Jin , Jian Ren , Jian Tang , Sijia Liu , Yanzhi Wang

The Lottery Ticket Hypothesis (LTH) states that a randomly-initialized large neural network contains a small sub-network (i.e., winning tickets) which, when trained in isolation, can achieve comparable performance to the large network. LTH…

Machine Learning · Computer Science 2023-05-23 Man Yao , Yuhong Chou , Guangshe Zhao , Xiawu Zheng , Yonghong Tian , Bo Xu , Guoqi Li

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

While self-attention mechanism has shown promising results for many vision tasks, it only considers the current features at a time. We show that such a manner cannot take full advantage of the attention mechanism. In this paper, we present…

Computer Vision and Pattern Recognition · Computer Science 2020-07-13 Xu Ma , Jingda Guo , Sihai Tang , Zhinan Qiao , Qi Chen , Qing Yang , Song Fu

The Lottery Ticket Hypothesis (LTH) posits that within overparametrized neural networks, there exist sparse subnetworks that are capable of matching the performance of the original model when trained in isolation from the original…

Quantum Physics · Physics 2026-01-29 Brandon Barton , Juan Carrasquilla , Christopher Roth , Agnes Valenti

Recently, Frankle & Carbin (2019) demonstrated that randomly-initialized dense networks contain subnetworks that once found can be trained to reach test accuracy comparable to the trained dense network. However, finding these high…

Machine Learning · Computer Science 2021-03-18 James Diffenderfer , Bhavya Kailkhura

The lottery ticket hypothesis has sparked the rapid development of pruning algorithms that aim to reduce the computational costs associated with deep learning during training and model deployment. Currently, such algorithms are primarily…

Machine Learning · Computer Science 2022-06-08 Jonas Fischer , Rebekka Burkholz

Recently, many plug-and-play self-attention modules are proposed to enhance the model generalization by exploiting the internal information of deep convolutional neural networks (CNNs). Previous works lay an emphasis on the design of…

Computer Vision and Pattern Recognition · Computer Science 2021-07-13 Zhongzhan Huang , Senwei Liang , Mingfu Liang , Wei He , Haizhao Yang

Lottery Ticket Hypothesis (LTH) raises keen attention to identifying sparse trainable subnetworks, or winning tickets, which can be trained in isolation to achieve similar or even better performance compared to the full models. Despite many…

Computer Vision and Pattern Recognition · Computer Science 2021-10-29 Xiaohan Chen , Yu Cheng , Shuohang Wang , Zhe Gan , Jingjing Liu , Zhangyang Wang

According to the Strong Lottery Ticket Hypothesis, every sufficiently large neural network with randomly initialized weights contains a sub-network which - still with its random weights - already performs as well for a given task as the…

Neural and Evolutionary Computing · Computer Science 2024-11-08 Philipp Altmann , Julian Schönberger , Maximilian Zorn , Thomas Gabor

The lottery ticket hypothesis (LTH) has attracted attention because it can explain why over-parameterized models often show high generalization ability. It is known that when we use iterative magnitude pruning (IMP), which is an algorithm…

Machine Learning · Computer Science 2022-09-29 Keitaro Sakamoto , Issei Sato

The lottery ticket hypothesis questions the role of overparameterization in supervised deep learning. But how is the performance of winning lottery tickets affected by the distributional shift inherent to reinforcement learning problems? In…

Machine Learning · Computer Science 2022-05-11 Marc Aurel Vischer , Robert Tjarko Lange , Henning Sprekeler

Recurrent neural networks (RNNs) and self-attention are both widely used sequence-mixing layers that maintain an internal memory. However, this memory is constructed using two orthogonal mechanisms: RNNs compress the entire past into a…

Machine Learning · Computer Science 2026-03-30 Leon Lufkin , Tomás Figliolia , Beren Millidge , Kamesh Krishnamurthy

The Lottery Ticket Hypothesis (LTH) states that for a reasonably sized neural network, a sub-network within the same network yields no less performance than the dense counterpart when trained from the same initialization. This work…

Machine Learning · Computer Science 2022-06-17 Surya Kant Sahu , Sai Mitheran , Somya Suhans Mahapatra

Convolutional Neural Networks (CNNs) have dominated computer vision for years, due to its ability in capturing locality and translation invariance. Recently, many vision transformer architectures have been proposed and they show promising…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Pichao Wang , Xue Wang , Fan Wang , Ming Lin , Shuning Chang , Hao Li , Rong Jin

The self-attention mechanism has emerged as a critical component for improving the performance of various backbone neural networks. However, current mainstream approaches individually incorporate newly designed self-attention modules (SAMs)…

Computer Vision and Pattern Recognition · Computer Science 2024-04-11 Zhongzhan Huang , Senwei Liang , Mingfu Liang , Liang Lin