English
Related papers

Related papers: The Effect of Attention Head Count on Transformer …

200 papers

Transformers achieve remarkable performance in several tasks but due to their quadratic complexity, with respect to the input's length, they are prohibitively slow for very long sequences. To address this limitation, we express the…

Machine Learning · Computer Science 2020-09-01 Angelos Katharopoulos , Apoorv Vyas , Nikolaos Pappas , François Fleuret

Deep learning employs multi-layer neural networks trained via the backpropagation algorithm. This approach has achieved success across many domains and relies on adaptive gradient methods such as the Adam optimizer. Sequence modeling…

Machine Learning · Computer Science 2025-07-16 Esmail Gumaan

Central to the success of Transformers is the attention block, which effectively models global dependencies among input tokens associated to a dataset. However, we theoretically demonstrate that standard attention mechanisms in transformers…

Machine Learning · Computer Science 2026-03-31 Hemanth Saratchandran

Transformer architectures have achieved state-of-the-art results on a variety of sequence modeling tasks. However, their attention mechanism comes with a quadratic complexity in sequence lengths, making the computational overhead…

Computation and Language · Computer Science 2022-06-03 Hao Peng , Jungo Kasai , Nikolaos Pappas , Dani Yogatama , Zhaofeng Wu , Lingpeng Kong , Roy Schwartz , Noah A. Smith

Despite their central role in the success of foundational models and large-scale language modeling, the theoretical foundations governing the operation of Transformers remain only partially understood. Contemporary research has largely…

Machine Learning · Computer Science 2025-06-02 Sagar Ghosh , Kushal Bose , Swagatam Das

With the attention mechanism, transformers achieve significant empirical successes. Despite the intuitive understanding that transformers perform relational inference over long sequences to produce desirable representations, we lack a…

Machine Learning · Computer Science 2024-04-02 Yufeng Zhang , Boyi Liu , Qi Cai , Lingxiao Wang , Zhaoran Wang

We explore the expressive power of Transformers by establishing precise approximation error upper and lower bounds for H\"{o}lder class. Specifically, a new approximation upper bound is derived for the standard Transformer architecture…

Machine Learning · Computer Science 2026-05-11 Xin He , Yuling Jiao , Xiliang Lu , Jerry Zhijian Yang

The Transformer architecture is widely applied in sequence modeling applications, yet the theoretical understanding of its working principles remains limited. In this work, we investigate the approximation rate for single-layer Transformers…

Machine Learning · Computer Science 2025-01-03 Haotian Jiang , Qianxiao Li

Despite the great success of Transformer networks in various applications such as natural language processing and computer vision, their theoretical aspects are not well understood. In this paper, we study the approximation and estimation…

Machine Learning · Computer Science 2024-03-26 Shokichi Takakura , Taiji Suzuki

Transformer-based models have brought a radical change to neural machine translation. A key feature of the Transformer architecture is the so-called multi-head attention mechanism, which allows the model to focus simultaneously on different…

Computation and Language · Computer Science 2020-10-06 Alessandro Raganato , Yves Scherrer , Jörg Tiedemann

The multi-head self-attention of popular transformer models is widely used within Natural Language Processing (NLP), including for the task of extractive summarization. With the goal of analyzing and pruning the parameter-heavy…

Computation and Language · Computer Science 2020-12-04 Wen Xiao , Patrick Huber , Giuseppe Carenini

Transformers have dominated sequence processing tasks for the past seven years -- most notably language modeling. However, the inherent quadratic complexity of their attention mechanism remains a significant bottleneck as context length…

Computation and Language · Computer Science 2025-10-08 Alexander M. Fichtl , Jeremias Bohn , Josefin Kelber , Edoardo Mosca , Georg Groh

Transformers have become the dominant architecture across a wide range of domains, largely due to the effectiveness of multi-head attention in capturing diverse representation subspaces. However, standard multi-head attention activates all…

Machine Learning · Computer Science 2026-04-27 Bilal Faye , Abdoulaye Mbaye , Hanane Azzag , Mustapha Lebbah

Since transformer was firstly published in 2017, several works have been proposed to optimize it. However, the major structure of transformer remains unchanged, ignoring one of its main intrinsic limitations, which is the same static value…

Machine Learning · Computer Science 2025-12-30 Xiaowei Wang

Transformer architectures have led to remarkable progress in many state-of-art applications. However, despite their successes, modern transformers rely on the self-attention mechanism, whose time- and space-complexity is quadratic in the…

Machine Learning · Computer Science 2022-09-13 Feyza Duman Keles , Pruthuvi Mahesakya Wijewardena , Chinmay Hegde

This paper studies the relative importance of attention heads in Transformer-based models to aid their interpretability in cross-lingual and multi-lingual tasks. Prior research has found that only a few attention heads are important in each…

Computation and Language · Computer Science 2021-08-20 Weicheng Ma , Kai Zhang , Renze Lou , Lili Wang , Soroush Vosoughi

Transformers are built upon multi-head scaled dot-product attention and positional encoding, which aim to learn the feature representations and token dependencies. In this work, we focus on enhancing the distinctive representation by…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Litao Yu , Jian Zhang

Transformers evaluated in a single, fixed-depth pass are provably limited in expressive power to the constant-depth circuit class TC0. Running a Transformer autoregressively removes that ceiling -- first in next-token prediction and, more…

Machine Learning · Computer Science 2025-07-21 Mrinal Mathur , Mike Doan , Barak Pearlmutter , Sergey Plis

Transformers have become a standard neural network architecture for many NLP problems, motivating theoretical analysis of their power in terms of formal languages. Recent work has shown that transformers with hard attention are quite…

Computation and Language · Computer Science 2022-04-12 William Merrill , Ashish Sabharwal , Noah A. Smith

Transformers are powerful sequence models, but require time and memory that grows quadratically with the sequence length. In this paper we introduce sparse factorizations of the attention matrix which reduce this to $O(n \sqrt{n})$. We also…

Machine Learning · Computer Science 2019-04-25 Rewon Child , Scott Gray , Alec Radford , Ilya Sutskever