English
Related papers

Related papers: Laplacian Heads Improve Transformers by Smoothing …

200 papers

Since its introduction, the transformer has shifted the development trajectory away from traditional models (e.g., RNN, MLP) in time series forecasting, which is attributed to its ability to capture global dependencies within temporal…

Machine Learning · Computer Science 2025-01-07 Xiwen Chen , Peijie Qiu , Wenhui Zhu , Huayu Li , Hao Wang , Aristeidis Sotiras , Yalin Wang , Abolfazl Razi

The quadratic complexity of self-attention in Transformers has hindered the processing of long text. To alleviate this problem, previous works have proposed to sparsify the attention matrix, taking advantage of the observation that crucial…

Computation and Language · Computer Science 2024-01-12 Ziwei He , Jian Yuan , Le Zhou , Jingwen Leng , Bo Jiang

Multilingual transformer-based models demonstrate remarkable zero and few-shot transfer across languages by learning and reusing language-agnostic features. However, as a fixed-size model acquires more languages, its performance across all…

Computation and Language · Computer Science 2023-05-08 William Held , Diyi Yang

Diffusion models, though successful, are known to suffer from hallucinations that create incoherent or unrealistic samples. Recent works have attributed this to the phenomenon of mode interpolation and score smoothening, but they lack a…

Computer Vision and Pattern Recognition · Computer Science 2025-11-13 Barath Chandran. C , Srinivas Anumasa , Dianbo Liu

Recent studies show that the attention heads in Transformer are not equal. We relate this phenomenon to the imbalance training of multi-head attention and the model dependence on specific heads. To tackle this problem, we propose a simple…

Computation and Language · Computer Science 2022-09-01 Zewei Sun , Shujian Huang , Xin-Yu Dai , Jiajun Chen

Transformers have demonstrated great success in numerous domains including natural language processing and bioinformatics. This success stems from the use of the attention mechanism by these models in order to represent and propagate…

Machine Learning · Computer Science 2025-02-10 Nathaniel Tomczak , Sanmukh Kuppannagari

Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in…

Computation and Language · Computer Science 2025-09-23 Asif Shahriar , Rifat Shahriyar , M Saifur Rahman

Various forms of sparse attention have been explored to mitigate the quadratic computational and memory cost of the attention mechanism in transformers. We study sparse transformers not through a lens of efficiency but rather in terms of…

Machine Learning · Computer Science 2025-06-19 Parikshit Ram , Kenneth L. Clarkson , Tim Klinger , Shashanka Ubaru , Alexander G. Gray

Transformer layers, which use an alternating pattern of multi-head attention and multi-layer perceptron (MLP) layers, provide an effective tool for a variety of machine learning problems. As the transformer layers use residual connections…

Machine Learning · Computer Science 2022-12-13 Yaofeng Desmond Zhong , Tongtao Zhang , Amit Chakraborty , Biswadip Dey

The quadratic complexity of the attention mechanism represents one of the biggest hurdles for processing long sequences using Transformers. Current methods, relying on sparse representations or stateful recurrence, sacrifice token-to-token…

Machine Learning · Computer Science 2025-06-06 Tobias Christian Nauen , Sebastian Palacio , Andreas Dengel

We propose a synthetic reasoning task, LEGO (Learning Equality and Group Operations), that encapsulates the problem of following a chain of reasoning, and we study how the Transformer architectures learn this task. We pay special attention…

Machine Learning · Computer Science 2023-02-21 Yi Zhang , Arturs Backurs , Sébastien Bubeck , Ronen Eldan , Suriya Gunasekar , Tal Wagner

To overcome the quadratic cost of self-attention, recent works have proposed various sparse attention modules, most of which fall under one of two groups: 1) sparse attention under a hand-crafted patterns and 2) full attention followed by a…

Machine Learning · Computer Science 2022-10-28 Sungjun Cho , Seonwoo Min , Jinwoo Kim , Moontae Lee , Honglak Lee , Seunghoon Hong

Softmax self-attention often assigns disproportionate weight to semantically uninformative tokens such as special tokens and punctuation, a phenomenon known as attention noise. While recent methods like Cog Attention and the Differential…

Computation and Language · Computer Science 2025-08-27 Ivan Kobyzev , Abbas Ghaddar , Dingtao Hu , Boxing Chen

Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision. However, Transformer training and inference in previous works…

Computer Vision and Pattern Recognition · Computer Science 2021-12-24 Zizheng Pan , Bohan Zhuang , Haoyu He , Jing Liu , Jianfei Cai

Multi-head attention powers Transformer networks, the primary deep learning architecture behind the success of large language models (LLMs). Yet, the theoretical advantages of multi-head versus single-head attention, beyond mere parallel…

Machine Learning · Computer Science 2025-11-11 Haitz Sáez de Ocáriz Borde

Transformers have become an important workhorse of machine learning, with numerous applications. This necessitates the development of reliable methods for increasing their transparency. Multiple interpretability methods, often based on…

Machine Learning · Computer Science 2022-06-24 Ameen Ali , Thomas Schnake , Oliver Eberle , Grégoire Montavon , Klaus-Robert Müller , Lior Wolf

Attending to what is relevant is fundamental to both the mammalian brain and modern machine learning models such as Transformers. Yet, determining relevance remains a core challenge, traditionally offloaded to learning algorithms like…

Machine Learning · Computer Science 2025-05-13 Ahsan Adeel

We study the effect of normalization schemes on token representations in deep transformers. Modeling their evolution as interacting particles on the sphere, we show that normalization acts as a form of speed regulation. This perspective…

Machine Learning · Computer Science 2025-11-12 Nikita Karagodin , Shu Ge , Yury Polyanskiy , Philippe Rigollet

The smallest eigenvectors of the graph Laplacian are well-known to provide a succinct representation of the geometry of a weighted graph. In reinforcement learning (RL), where the weighted graph may be interpreted as the state transition…

Machine Learning · Computer Science 2018-10-11 Yifan Wu , George Tucker , Ofir Nachum

Structured dropout approaches, such as attention dropout and DropHead, have been investigated to regularize the multi-head attention mechanism in Transformers. In this paper, we propose a new regularization scheme based on token-level…

Computation and Language · Computer Science 2023-10-31 Yangjun Wu , Kebin Fang , Dongxiang Zhang , Han Wang , Hao Zhang , Gang Chen
‹ Prev 1 3 4 5 6 7 10 Next ›