English
Related papers

Related papers: Hardware-aligned Hierarchical Sparse Attention for…

200 papers

Multi-headed Attention's (MHA) quadratic compute and linearly growing KV-cache make long-context transformers expensive to train and serve. Prior works such as Grouped Query Attention (GQA) and Multi-Latent Attention (MLA) shrink the cache,…

Computation and Language · Computer Science 2026-03-18 Tomas Figliolia , Nicholas Alonso , Rishi Iyer , Quentin Anthony , Beren Millidge

Efficient Transformers have been developed for long sequence modeling, due to their subquadratic memory and time complexity. Sparse Transformer is a popular approach to improving the efficiency of Transformers by restricting self-attention…

Machine Learning · Computer Science 2023-02-01 Aosong Feng , Irene Li , Yuang Jiang , Rex Ying

In Sequential Recommendation Systems (SRSs), Transformer models have demonstrated remarkable performance but face computational and memory cost challenges, especially when modeling long-term user behavior sequences. Due to its quadratic…

Information Retrieval · Computer Science 2026-03-25 Juntao Hu , Wei Zhou , Haini Cai , Xiao Du , Huayi Shen , Junhao Wen

Transformers have demonstrated strong performance across a wide range of sequence modeling tasks, but their quadratic attention complexity limits scalability to long sequences. Linear models such as Mamba and sliding-window attention (SWA)…

Machine Learning · Computer Science 2025-09-03 Aref Jafari , Yuhe Fan , Benyamin Jamialahmadi , Parsa Farinneya , Boxing Chen , Marzieh S. Tahaei

Recurrent Neural Networks architectures excel at processing sequences by modelling dependencies over different timescales. The recently introduced Recurrent Weighted Average (RWA) unit captures long term dependencies far better than an LSTM…

Machine Learning · Computer Science 2017-06-20 Brendan Maginnis , Pierre H. Richemond

The Transformer architecture, despite its widespread success, struggles with long-context scenarios due to quadratic computation and linear memory growth. While various linear attention variants mitigate these efficiency constraints by…

Machine Learning · Computer Science 2025-10-02 Yuqi Pan , Yongqi An , Zheng Li , Yuhong Chou , Ruijie Zhu , Xiaohui Wang , Mingxuan Wang , Jinqiao Wang , Guoqi Li

Recent advances in deep learning have relied heavily on the use of large Transformers due to their ability to learn at scale. However, the core building block of Transformers, the attention operator, exhibits quadratic cost in sequence…

With the explosive growth of data, long-sequence modeling has become increasingly important in tasks such as natural language processing and bioinformatics. However, existing methods face inherent trade-offs between efficiency and memory.…

Machine Learning · Computer Science 2025-10-07 Youjin Wang , Yangjingyi Chen , Jiahao Yan , Jiaxuan Lu , Xiao Sun

Sparse attention reduces the quadratic complexity of full self-attention but faces two challenges: (1) an attention gap, where applying sparse attention to full-attention-trained models causes performance degradation due to train-inference…

Computation and Language · Computer Science 2026-02-02 Zhenyi Shen , Junru Lu , Lin Gui , Jiazheng Li , Yulan He , Di Yin , Xing Sun

The advent of Transformers marked a significant breakthrough in sequence modelling, providing a highly performant architecture capable of leveraging GPU parallelism. However, Transformers are computationally expensive at inference time,…

Machine Learning · Computer Science 2024-05-29 Leo Feng , Frederick Tung , Hossein Hajimirsadeghi , Mohamed Osama Ahmed , Yoshua Bengio , Greg Mori

Self-Supervised Learning (SSL) has proven to be effective in various domains, including speech processing. However, SSL is computationally and memory expensive. This is in part due the quadratic complexity of multi-head self-attention…

Machine Learning · Computer Science 2024-09-05 Ryan Whetten , Titouan Parcollet , Adel Moumen , Marco Dinarelli , Yannick Estève

Attention mechanisms underpin modern deep learning, while the quadratic time and space complexity limit scalability for long sequences. To address this, Quantum Annealing Multi-Head Attention (QAMA) is proposed, a novel drop-in operator…

Quantum Physics · Physics 2025-10-14 Peng Du , Jinjing Shi , Wenxuan Wang , Yin Ma , Kai Wen , Xuelong Li

Attention mechanisms have significantly advanced visual models by capturing global context effectively. However, their reliance on large-scale datasets and substantial computational resources poses challenges in data-scarce and…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Chenghao Li , Chaoning Zhang , Boheng Zeng , Yi Lu , Pengbo Shi , Qingzi Chen , Jirui Liu , Lingyun Zhu , Yang Yang , Heng Tao Shen

Modern recommender systems leverage ultra-long user behavior sequences to capture dynamic preferences, but end-to-end modeling is infeasible in production due to latency and memory constraints. While summarizing history via interest centers…

Information Retrieval · Computer Science 2026-02-25 Kun Yuan , Junyu Bi , Daixuan Cheng , Changfa Wu , Shuwen Xiao , Binbin Cao , Jian Wu , Yuning Jiang

Hyperspectral image (HSI) classification faces critical challenges, including high spectral dimensionality, complex spectral-spatial correlations, and limited training samples with severe class imbalance. While CNNs excel at local feature…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Asmit Bandyopadhyay , Anindita Das Bhattacharjee , Rakesh Das

Transformers have become the foundation of numerous state-of-the-art AI models across diverse domains, thanks to their powerful attention mechanism for modeling long-range dependencies. However, the quadratic scaling complexity of attention…

Hardware Architecture · Computer Science 2026-01-29 Zhenkun Fan , Zishen Wan , Che-Kai Liu , Ashwin Sanjay Lele , Win-San Khwa , Bo Zhang , Meng-Fan Chang , Arijit Raychowdhury

In recent years, self-attention has become the dominant paradigm for sequence modeling in a variety of domains. However, in domains with very long sequence lengths the $\mathcal{O}(T^2)$ memory and $\mathcal{O}(T^2 H)$ compute costs can…

Machine Learning · Computer Science 2023-06-01 Mohammad Mahmudul Alam , Edward Raff , Stella Biderman , Tim Oates , James Holt

Attention is the critical component of a transformer. Yet the quadratic computational complexity of vanilla full attention in the input size and the inability of its linear attention variant to focus have been challenges for computer vision…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Nhat Thanh Tran , Fanghui Xue , Shuai Zhang , Jiancheng Lyu , Yunling Zheng , Yingyong Qi , Jack Xin

Hypergraphs serve as an effective model for depicting complex connections in various real-world scenarios, from social to biological networks. The development of Hypergraph Neural Networks (HGNNs) has emerged as a valuable method to manage…

Machine Learning · Computer Science 2024-06-17 Shuai Wang , David W. Zhang , Jia-Hong Huang , Stevan Rudinac , Monika Kackovic , Nachoem Wijnberg , Marcel Worring

Recently Transformers have provided state-of-the-art performance in sparse matching, crucial to realize high-performance 3D vision applications. Yet, these Transformers lack efficiency due to the quadratic computational complexity of their…

Computer Vision and Pattern Recognition · Computer Science 2022-04-25 Suwichaya Suwanwimolkul , Satoshi Komorita