English
Related papers

Related papers: Wavy Transformer

200 papers

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…

Machine Learning · Computer Science 2026-01-14 Xin Dai , Pengcheng Huang , Zhenghao Liu , Shuo Wang , Yukun Yan , Chaojun Xiao , Yu Gu , Ge Yu , Maosong Sun

Transformers have achieved extraordinary success in modern machine learning due to their excellent ability to handle sequential data, especially in next-token prediction (NTP) tasks. However, the theoretical understanding of their…

Machine Learning · Computer Science 2024-10-01 Ruiquan Huang , Yingbin Liang , Jing Yang

We propose a novel neural network architecture, the normalized Transformer (nGPT) with representation learning on the hypersphere. In nGPT, all vectors forming the embeddings, MLP, attention matrices and hidden states are unit norm…

Machine Learning · Computer Science 2025-04-25 Ilya Loshchilov , Cheng-Ping Hsieh , Simeng Sun , Boris Ginsburg

Geometric deep learning has made great strides towards generalizing the design of structure-aware neural networks from traditional domains to non-Euclidean ones, giving rise to graph neural networks (GNN) that can be applied to…

Machine Learning · Statistics 2024-10-28 Frederik Wenkel , Yimeng Min , Matthew Hirn , Michael Perlmutter , Guy Wolf

Transformer has been widely used for self-supervised pre-training in Natural Language Processing (NLP) and achieved great success. However, it has not been fully explored in visual self-supervised learning. Meanwhile, previous methods only…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Zhaowen Li , Zhiyang Chen , Fan Yang , Wei Li , Yousong Zhu , Chaoyang Zhao , Rui Deng , Liwei Wu , Rui Zhao , Ming Tang , Jinqiao Wang

Graph Convolutional Networks (GCNs) are powerful for processing graph-structured data and have achieved state-of-the-art performance in several tasks such as node classification, link prediction, and graph classification. However, it is…

Machine Learning · Computer Science 2021-10-19 Langzhang Liang , Cuiyun Gao , Shiyi Chen , Shishi Duan , Yu pan , Junjin Zheng , Lei Wang , Zenglin Xu

Temporal Graph Neural Networks have garnered substantial attention for their capacity to model evolving structural and temporal patterns while exhibiting impressive performance. However, it is known that these architectures are encumbered…

Machine Learning · Computer Science 2024-02-12 Mahdi Biparva , Raika Karimi , Faezeh Faez , Yingxue Zhang

Vision Transformer (ViT) has recently demonstrated promise in computer vision problems. However, unlike Convolutional Neural Networks (CNN), it is known that the performance of ViT saturates quickly with depth increasing, due to the…

Computer Vision and Pattern Recognition · Computer Science 2022-03-14 Peihao Wang , Wenqing Zheng , Tianlong Chen , Zhangyang Wang

Transformers, the standard implementation for large language models (LLMs), typically consist of tens to hundreds of discrete layers. While more layers can lead to better performance, this approach has been challenged as far from efficient,…

Machine Learning · Computer Science 2025-05-21 Yen-Chen Wu , Feng-Ting Liao , Meng-Hsi Chen , Pei-Chen Ho , Farhang Nabiei , Da-shan Shiu

The drastic performance degradation of Graph Neural Networks (GNNs) as the depth of the graph propagation layers exceeds 8-10 is widely attributed to a phenomenon of Over-smoothing. Although recent research suggests that Over-smoothing may…

Machine Learning · Computer Science 2024-08-08 Jie Peng , Runlin Lei , Zhewei Wei

The complicated syntax structure of natural language is hard to be explicitly modeled by sequence-based models. Graph is a natural structure to describe the complicated relation between tokens. The recent advance in Graph Neural Networks…

Computation and Language · Computer Science 2019-09-19 Wei Li , Shuheng Li , Shuming Ma , Yancheng He , Deli Chen , Xu Sun

Attention-based transformers have been remarkably successful at modeling generative processes across various domains and modalities. In this paper, we study the behavior of transformers on data drawn from \kth Markov processes, where the…

Machine Learning · Computer Science 2024-07-26 Nived Rajaraman , Marco Bondaschi , Kannan Ramchandran , Michael Gastpar , Ashok Vardhan Makkuva

In spite of their huge success, transformer models remain difficult to scale in depth. In this work, we develop a unified signal propagation theory and provide formulae that govern the moments of the forward and backward signal through the…

Computation and Language · Computer Science 2024-07-19 Akhil Kedia , Mohd Abbas Zaidi , Sushil Khyalia , Jungho Jung , Harshith Goka , Haejun Lee

Transformers have significantly advanced the field of natural language processing, but comprehending their internal mechanisms remains a challenge. In this paper, we introduce a novel geometric perspective that elucidates the inner…

Computation and Language · Computer Science 2023-09-20 Raul Molina

The dominant paradigm for learning on graph-structured data is message passing. Despite being a strong inductive bias, the local message passing mechanism suffers from pathological issues such as over-smoothing, over-squashing, and limited…

Machine Learning · Computer Science 2025-04-15 Jacob Bamberger , Federico Barbero , Xiaowen Dong , Michael M. Bronstein

Transformers have become the dominant architecture for sequence modeling tasks such as natural language processing or audio processing, and they are now even considered for tasks that are not naturally sequential such as image…

Machine Learning · Computer Science 2024-03-05 Jorg Bornschein , Yazhe Li , Amal Rannen-Triki

A few models have tried to tackle the link prediction problem, also known as knowledge graph completion, by embedding knowledge graphs in comparably lower dimensions. However, the state-of-the-art results are attained at the cost of…

Machine Learning · Computer Science 2022-11-29 Peyman Baghershahi , Reshad Hosseini , Hadi Moradi

In this paper, we describe the use of recurrent neural networks to capture sequential information from the self-attention representations to improve the Transformers. Although self-attention mechanism provides a means to exploit long…

Computation and Language · Computer Science 2021-04-06 Tze Yuang Chong , Xuyang Wang , Lin Yang , Junjie Wang

The large attention-based encoder-decoder network (Transformer) has become prevailing recently due to its effectiveness. But the high computation complexity of its decoder raises the inefficiency issue. By examining the mathematic…

Computation and Language · Computer Science 2023-05-12 Yanyang Li , Ye Lin , Tong Xiao , Jingbo Zhu

Although it is known that transformer language models (LMs) pass features from early layers to later layers, it is not well understood how this information is represented and routed by the model. We analyze a mechanism used in two LMs to…

Computation and Language · Computer Science 2025-05-12 Jack Merullo , Carsten Eickhoff , Ellie Pavlick