English
Related papers

Related papers: Star-Transformer

200 papers

Turning the weights to zero when training a neural network helps in reducing the computational complexity at inference. To progressively increase the sparsity ratio in the network without causing sharp weight discontinuities during…

Computer Vision and Pattern Recognition · Computer Science 2023-01-25 Antoine Vanderschueren , Christophe De Vleeschouwer

Transformer-based architectures have achieved remarkable success in natural language processing and computer vision. However, their performance in multivariate long-term forecasting often falls short compared to simpler linear baselines.…

Machine Learning · Computer Science 2025-07-09 Dizhen Liang

Despite the exciting performance, Transformer is criticized for its excessive parameters and computation cost. However, compressing Transformer remains as an open problem due to its internal complexity of the layer designs, i.e., Multi-Head…

Computer Vision and Pattern Recognition · Computer Science 2022-05-25 Gen Luo , Yiyi Zhou , Xiaoshuai Sun , Yan Wang , Liujuan Cao , Yongjian Wu , Feiyue Huang , Rongrong Ji

In the post-deep learning era, the Transformer architecture has demonstrated its powerful performance across pre-trained big models and various downstream tasks. However, the enormous computational demands of this architecture have deterred…

Recent progress on parse tree encoder for sentence representation learning is notable. However, these works mainly encode tree structures recursively, which is not conducive to parallelization. On the other hand, these works rarely take…

Computation and Language · Computer Science 2022-05-10 Junhua Ma , Jiajun Li , Yuxuan Liu , Shangbo Zhou , Xue Li

This paper addresses the topic of sparsifying deep neural networks (DNN's). While DNN's are powerful models that achieve state-of-the-art performance on a large number of tasks, the large number of model parameters poses serious storage and…

Machine Learning · Computer Science 2018-02-07 Igor Fedorov , Bhaskar D. Rao

This work presents an analysis of the effectiveness of using standard shallow feed-forward networks to mimic the behavior of the attention mechanism in the original Transformer model, a state-of-the-art architecture for sequence-to-sequence…

Computation and Language · Computer Science 2024-02-06 Vukasin Bozic , Danilo Dordevic , Daniele Coppola , Joseph Thommes , Sidak Pal Singh

Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy by keeping data local. Traditional FL approaches rely on a centralized, star-shaped topology, where a central server…

Machine Learning · Computer Science 2025-11-25 Mirko Konstantin , Anirban Mukhopadhyay

In this paper, we introduce \texttt{IAFormer}, a novel Transformer-based architecture that efficiently integrates pairwise particle interactions through a dynamic sparse attention mechanism. \texttt{IAFormer} has two new mechanisms within…

High Energy Physics - Phenomenology · Physics 2026-04-21 W. Esmail , A. Hammad , M. Nojiri

Self-attention mechanism is the key of the Transformer but often criticized for its computation demands. Previous token pruning works motivate their methods from the view of computation redundancy but still need to load the full network and…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Sihao Lin , Pumeng Lyu , Dongrui Liu , Tao Tang , Xiaodan Liang , Andy Song , Xiaojun Chang

We propose a generalization of transformer neural network architecture for arbitrary graphs. The original transformer was designed for Natural Language Processing (NLP), which operates on fully connected graphs representing all connections…

Machine Learning · Computer Science 2021-01-26 Vijay Prakash Dwivedi , Xavier Bresson

Accurate thermospheric density prediction is crucial for reliable satellite operations in Low Earth Orbits, especially at high solar and geomagnetic activity. Physics-based models such as TIE-GCM offer high fidelity but are computationally…

Space Physics · Physics 2026-03-30 Cedric Bös , Alessandro Bortotto , Mohamed Khalil Ben-Larbi

The reconstruction of micro-Doppler signatures of human movements is a key enabler for fine-grained activity recognition wireless sensing. In Joint Communication and Sensing (JCS) systems, unlike in dedicated radar sensing systems, a…

Signal Processing · Electrical Eng. & Systems 2024-02-06 Riccardo Mazzieri , Jacopo Pegoraro , Michele Rossi

Many recent deep learning-based solutions have widely adopted the attention-based mechanism in various tasks of the NLP discipline. However, the inherent characteristics of deep learning models and the flexibility of the attention mechanism…

Computation and Language · Computer Science 2023-10-09 Dairui Liu , Derek Greene , Ruihai Dong

Transformers have achieved remarkable success across natural language processing (NLP) and computer vision (CV). However, deep transformer models often suffer from an over-smoothing issue, in which token representations converge to similar…

Machine Learning · Computer Science 2025-10-21 Satoshi Noguchi , Yoshinobu Kawahara

Recently, Transformer-based networks have shown great promise on skeleton-based action recognition tasks. The ability to capture global and local dependencies is the key to success while it also brings quadratic computation and memory cost.…

Computer Vision and Pattern Recognition · Computer Science 2024-03-27 Qingtian Wang , Jianlin Peng , Shuze Shi , Tingxi Liu , Jiabin He , Renliang Weng

Recurrent Neural Networks have long been the dominating choice for sequence modeling. However, it severely suffers from two issues: impotent in capturing very long-term dependencies and unable to parallelize the sequential computation…

Machine Learning · Computer Science 2019-07-15 Zhiwei Wang , Yao Ma , Zitao Liu , Jiliang Tang

Learning predictive models from observations using deep neural networks (DNNs) is a promising new approach to many real-world planning and control problems. However, common DNNs are too unstructured for effective planning, and current…

Robotics · Computer Science 2023-12-21 Ziang Liu , Genggeng Zhou , Jeff He , Tobia Marcucci , Li Fei-Fei , Jiajun Wu , Yunzhu Li

Transformer plays a central role in many fundamental deep learning models, e.g., the ViT in computer vision and the BERT and GPT in natural language processing, whose effectiveness is mainly attributed to its multi-head attention (MHA)…

Machine Learning · Computer Science 2024-10-16 Shen Yuan , Hongteng Xu

Sparsity is regarded as a desirable property of representations, especially in terms of explanation. However, its usage has been limited due to the gap with dense representations. Most NLP research progresses in recent years are based on…

Computation and Language · Computer Science 2019-11-11 Wenpeng Hu , Mengyu Wang , Bing Liu , Feng Ji , Haiqing Chen , Dongyan Zhao , Jinwen Ma , Rui Yan