English
Related papers

Related papers: Sparse Universal Transformer

200 papers

The sparse transformer can reduce the computational complexity of the self-attention layers to $O(n)$, whilst still being a universal approximator of continuous sequence-to-sequence functions. However, this permutation variant operation is…

Machine Learning · Computer Science 2023-03-01 Shidi Li , Christian Walder , Alexander Soen , Lexing Xie , Miaomiao Liu

We propose a parameter sharing method for Transformers (Vaswani et al., 2017). The proposed approach relaxes a widely used technique, which shares parameters for one layer with all layers such as Universal Transformers (Dehghani et al.,…

Computation and Language · Computer Science 2023-06-05 Sho Takase , Shun Kiyono

Natural language processing (NLP) made an impressive jump with the introduction of Transformers. ChatGPT is one of the most famous examples, changing the perception of the possibilities of AI even outside the research community. However,…

Machine Learning · Computer Science 2023-07-06 Silas Alberti , Niclas Dern , Laura Thesing , Gitta Kutyniok

The problem of signal detection using a flexible and general model is considered. Due to applicability and flexibility of sparse signal representation and approximation, it has attracted a lot of attention in many signal processing areas.…

Information Theory · Computer Science 2016-02-17 Mohsen Joneidi , Parvin Ahmadi , Mostafa Sadeghi , Nazanin Rahnavard

Transformer-based approaches have revolutionized image super-resolution by modeling long-range dependencies. However, the quadratic computational complexity of vanilla self-attention mechanisms poses significant challenges, often leading to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Dinh Phu Tran , Thao Do , Saad Wazir , Seongah Kim , Seon Kwon Kim , Daeyoung Kim

Efficient large-scale inference of transformer-based large language models (LLMs) remains a fundamental systems challenge, frequently requiring multi-GPU parallelism to meet stringent latency and throughput targets. Conventional tensor…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-10 Chong Wang , Nan Du , Tom Gunter , Tao Lei , Kulin Seth , Senyu Tong , Jianyu Wang , Guoli Yin , Xiyou Zhou , Kelvin Zou , Ruoming Pang

Sparse expert models are a thirty-year old concept re-emerging as a popular architecture in deep learning. This class of architecture encompasses Mixture-of-Experts, Switch Transformers, Routing Networks, BASE layers, and others, all with…

Machine Learning · Computer Science 2022-09-07 William Fedus , Jeff Dean , Barret Zoph

Transformer has been widely adopted in Neural Machine Translation (NMT) because of its large capacity and parallel training of sequence generation. However, the deployment of Transformer is challenging because different scenarios require…

Computation and Language · Computer Science 2021-06-21 Peng Gao , Shijie Geng , Yu Qiao , Xiaogang Wang , Jifeng Dai , Hongsheng Li

A novel Transformer variation architecture is proposed in the implicit sparse style. Unlike "traditional" Transformers, instead of attention to sequential or batch entities in their entirety of whole dimensionality, in the proposed Batch…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Stanislav Selitskiy

We combine the capacity of sparsely gated Mixture-of-Experts (MoE) with the speed and stability of linear, mixing transformations to design the Sparse Mixer encoder model. Sparse Mixer slightly outperforms (<1%) BERT on GLUE and SuperGLUE,…

Machine Learning · Computer Science 2022-10-14 James Lee-Thorp , Joshua Ainslie

Parameter-efficient transfer learning (PETL), i.e., fine-tuning a small portion of parameters, is an effective strategy for adapting pre-trained models to downstream domains. To further reduce the memory demand, recent PETL works focus on…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Haiwen Diao , Bo Wan , Ying Zhang , Xu Jia , Huchuan Lu , Long Chen

Sparse data models, where data is assumed to be well represented as a linear combination of a few elements from a dictionary, have gained considerable attention in recent years, and their use has led to state-of-the-art results in many…

Information Theory · Computer Science 2015-03-13 Ignacio Ramirez , Guillermo Sapiro

Sparse matrix vector multiplication (SpMV) is an important kernel in scientific and engineering applications. The previous optimizations are sparse matrix format specific and expose the choice of the best format to application programmers.…

Mathematical Software · Computer Science 2012-10-10 Jiajia Li , Xiuxia Zhang , Guangming Tan , Mingyu Chen

Solid results from Transformers have made them prevailing architectures in various natural language and vision tasks. As a default component in Transformers, Layer Normalization (LN) normalizes activations within each token to boost the…

Computer Vision and Pattern Recognition · Computer Science 2022-08-03 Qiming Yang , Kai Zhang , Chaoxiang Lan , Zhi Yang , Zheyang Li , Wenming Tan , Jun Xiao , Shiliang Pu

We introduce the Normalized Matching Transformer (NMT), a deep learning approach for efficient and accurate sparse semantic keypoint matching between image pairs. NMT consists of a strong visual backbone, geometric feature refinement via…

Computer Vision and Pattern Recognition · Computer Science 2026-05-06 Abtin Pourhadi , Paul Swoboda

Deep neural networks have long been criticized for being black-box. To unveil the inner workings of modern neural architectures, a recent work \cite{yu2024white} proposed an information-theoretic objective function called Sparse Rate…

Machine Learning · Computer Science 2024-11-27 Yunzhe Hu , Difan Zou , Dong Xu

Large language models (LLMs) are popular around the world due to their powerful understanding capabilities. As the core component of LLMs, accelerating Transformer through parallelization has gradually become a hot research topic. Mask…

Machine Learning · Computer Science 2026-05-29 Wenhao Dai , Haodong Deng , Mengfei Rong , Xinyu Yang , Hongyu Liu , Fangxin Liu , Hailong Yang , Qianwen Cao , Qingxiao Sun

Fine-tuning the entire set of parameters of a large pretrained model has become the mainstream approach for transfer learning. To increase its efficiency and prevent catastrophic forgetting and interference, techniques like adapters and…

Computation and Language · Computer Science 2023-02-10 Alan Ansell , Edoardo Maria Ponti , Anna Korhonen , Ivan Vulić

Despite their practical success, modern seq2seq architectures are unable to generalize systematically on several SCAN tasks. Hence, it is not clear if SCAN-style compositional generalization is useful in realistic NLP tasks. In this work,…

Computation and Language · Computer Science 2021-09-17 Rahma Chaabouni , Roberto Dessì , Eugene Kharitonov

Recent advances in multilingual dependency parsing have brought the idea of a truly universal parser closer to reality. However, cross-language interference and restrained model capacity remain major obstacles. To address this, we propose a…

Computation and Language · Computer Science 2020-10-07 Ahmet Üstün , Arianna Bisazza , Gosse Bouma , Gertjan van Noord