English
Related papers

Related papers: Wavy Transformer

200 papers

Understanding the fundamental mechanism behind the success of transformer networks is still an open problem in the deep learning literature. Although their remarkable performance has been mostly attributed to the self-attention mechanism,…

Machine Learning · Computer Science 2022-11-23 Tolga Ergen , Behnam Neyshabur , Harsh Mehta

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

Machine Learning · Computer Science 2025-07-01 Venmugil Elango

Graph Convolutional Networks (GCNs) suffer from severe performance degradation in deep architectures due to over-smoothing. While existing studies primarily attribute the over-smoothing to repeated applications of graph Laplacian operators,…

Machine Learning · Computer Science 2025-07-23 Furong Peng , Jinzhen Gao , Xuan Lu , Kang Liu , Yifan Huo , Sheng Wang

A common issue in Graph Neural Networks (GNNs) is known as over-smoothing. By increasing the number of iterations within the message-passing of GNNs, the nodes' representations of the input graph align with each other and become…

Machine Learning · Computer Science 2021-10-22 Christian M. M. Frey , Yunpu Ma , Matthias Schubert

Transformer has been applied in the field of computer vision due to its excellent performance in natural language processing, surpassing traditional convolutional neural networks and achieving new state-of-the-art. ViT divides an image into…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Yuang Liu , Zhiheng Qiu , Xiaokai Qin

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

Attention, specifically scaled dot-product attention, has proven effective for natural language, but it does not have a mechanism for handling hierarchical patterns of arbitrary nesting depth, which limits its ability to recognize certain…

Computation and Language · Computer Science 2024-01-25 Brian DuSell , David Chiang

Currently, this paper is under review in IEEE. Transformers have intrigued the vision research community with their state-of-the-art performance in natural language processing. With their superior performance, transformers have found their…

Computer Vision and Pattern Recognition · Computer Science 2022-10-05 Preetam Ghosh , Swalpa Kumar Roy , Bikram Koirala , Behnood Rasti , Paul Scheunders

Despite the Transformer's dominance across machine learning, its architecture remains largely heuristic and lacks a unified theoretical foundation. We introduce Score-based Variational Flow (SVFlow), a continuous-time dynamical system for…

Machine Learning · Computer Science 2026-04-28 Huadong Liao

Graphs are useful for representing various realworld objects. However, graph neural networks (GNNs) tend to suffer from over-smoothing, where the representations of nodes of different classes become similar as the number of layers…

Machine Learning · Computer Science 2024-10-22 Jun Kato , Airi Mita , Keita Gobara , Akihiro Inokuchi

In contrast to RNNs, which compress their history into a single hidden state, Transformers can attend to all past tokens directly. However, standard Transformers rely solely on the hidden state from the previous layer to represent the…

Machine Learning · Computer Science 2025-05-29 Gleb Gerasimov , Yaroslav Aksenov , Nikita Balagansky , Viacheslav Sinii , Daniil Gavrilov

Non-autoregressive text to speech (NAR-TTS) models have attracted much attention from both academia and industry due to their fast generation speed. One limitation of NAR-TTS models is that they ignore the correlation in time and frequency…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-01 Yi Ren , Xu Tan , Tao Qin , Zhou Zhao , Tie-Yan Liu

The vanilla Graph Convolutional Network (GCN) uses a low-pass filter to extract low-frequency signals from graph topology, which may lead to the over-smoothing problem when GCN goes deep. To this end, various methods have been proposed to…

Machine Learning · Computer Science 2024-02-13 Chen Huang , Haoyang Li , Yifan Zhang , Wenqiang Lei , Jiancheng Lv

Transformer-based pre-trained models have gained much advance in recent years, becoming one of the most important backbones in natural language processing. Recent work shows that the attention mechanism inside Transformer may not be…

Computation and Language · Computer Science 2022-10-27 Yile Wang , Linyi Yang , Zhiyang Teng , Ming Zhou , Yue Zhang

Understanding the training dynamics of transformers is important to explain the impressive capabilities behind large language models. In this work, we study the dynamics of training a shallow transformer on a task of recognizing…

Machine Learning · Computer Science 2024-10-15 Hongru Yang , Bhavya Kailkhura , Zhangyang Wang , Yingbin Liang

Sheaf Neural Networks (SNNs) were introduced as an extension of Graph Convolutional Networks to address oversmoothing on heterophilous graphs by attaching a sheaf to the input graph and replacing the adjacency-based operator with a sheaf…

Machine Learning · Computer Science 2026-03-06 Ferran Hernandez Caralt , Mar Gonzàlez i Català , Adrián Bazaga , Pietro Liò

Learning algorithms become more powerful, often at the cost of increased complexity. In response, the demand for algorithms to be transparent is growing. In NLP tasks, attention distributions learned by attention-based deep learning models…

Computation and Language · Computer Science 2019-07-09 Joris Baan , Maartje ter Hoeve , Marlies van der Wees , Anne Schuth , Maarten de Rijke

Oversmoothing is a common challenge in learning graph neural networks (GNN), where, as layers increase, embedding features learned from GNNs quickly become similar or indistinguishable, making them incapable of differentiating network…

Machine Learning · Computer Science 2025-07-22 Yufei Jin , Xingquan Zhu

Transformer architecture has shown impressive performance in multiple research domains and has become the backbone of many neural network models. However, there is limited understanding on how it works. In particular, with a simple…

Computation and Language · Computer Science 2023-10-31 Yuandong Tian , Yiping Wang , Beidi Chen , Simon Du

Masked diffusion models (MDMs), which leverage bidirectional attention and a denoising process, are narrowing the performance gap with autoregressive models (ARMs). However, their internal attention mechanisms remain under-explored. This…

Artificial Intelligence · Computer Science 2026-01-13 Pengcheng Huang , Tianming Liu , Zhenghao Liu , Yukun Yan , Shuo Wang , Tong Xiao , Zulong Chen , Maosong Sun