English
Related papers

Related papers: Translational Equivariance in Kernelizable Attenti…

200 papers

Vision Transformers have achieved state-of-the-art performance in many visual tasks. Due to the quadratic computational and memory complexities of self-attention, recent works either apply attention only to low-resolution inputs or restrict…

Computer Vision and Pattern Recognition · Computer Science 2022-07-05 Cheng Li , Yangxin Liu

Transformer models are permutation equivariant. To supply the order and type information of the input tokens, position and segment embeddings are usually added to the input. Recent works proposed variations of positional encodings with…

Computation and Language · Computer Science 2021-11-04 Pu-Chin Chen , Henry Tsai , Srinadh Bhojanapalli , Hyung Won Chung , Yin-Wen Chang , Chun-Sung Ferng

Graph learning architectures based on the k-dimensional Weisfeiler-Leman (k-WL) hierarchy offer a theoretically well-understood expressive power. However, such architectures often fail to deliver solid predictive performance on real-world…

Machine Learning · Computer Science 2024-11-11 Luis Müller , Daniel Kusuma , Blai Bonet , Christopher Morris

Natural languages are believed to be (mildly) context-sensitive. Despite underpinning remarkably capable large language models, transformers are unable to model many context-free language tasks. In an attempt to address this limitation in…

Computation and Language · Computer Science 2024-05-15 Jiaoda Li , Jennifer C. White , Mrinmaya Sachan , Ryan Cotterell

Group equivariant neural networks are used as building blocks of group invariant neural networks, which have been shown to improve generalisation performance and data efficiency through principled parameter sharing. Such works have mostly…

Machine Learning · Computer Science 2021-06-17 Michael Hutchinson , Charline Le Lan , Sheheryar Zaidi , Emilien Dupont , Yee Whye Teh , Hyunjik Kim

Convolutional neural networks have shown remarkable performance in recent years on various computer vision problems. However, the traditional convolutional neural network architecture lacks a critical property: shift equivariance and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Quentin Gabot , Teck-Yian Lim , Jérémy Fix , Joana Frontera-Pons , Chengfang Ren , Jean-Philippe Ovarlez

Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding. Both are interfaced with an attention…

Computation and Language · Computer Science 2018-11-02 Maha Elbayad , Laurent Besacier , Jakob Verbeek

Transformers, known for their attention mechanisms, have proven highly effective in focusing on critical elements within complex data. This feature can effectively be used to address the time-varying channels in wireless communication…

Machine Learning · Computer Science 2024-12-03 Matin Mortaheb , Mohammad A. Amir Khojastepour , Sennur Ulukus

The global attention mechanism is one of the keys to the success of transformer architecture, but it incurs quadratic computational costs in relation to the number of tokens. On the other hand, equivariant models, which leverage the…

Machine Learning · Computer Science 2025-09-30 Owen Lewis Howell , Linfeng Zhao , Xupeng Zhu , Yaoyao Qian , Haojie Huang , Lingfeng Sun , Wil Thomason , Robert Platt , Robin Walters

Equivariant Transformers such as Equiformer have demonstrated the efficacy of applying Transformers to the domain of 3D atomistic systems. However, they are limited to small degrees of equivariant representations due to their computational…

Machine Learning · Computer Science 2024-03-08 Yi-Lun Liao , Brandon Wood , Abhishek Das , Tess Smidt

Revolutionizing the field of deep learning, Transformer-based models have achieved remarkable performance in many tasks. Recent research has recognized these models are robust to shuffling but are limited to inter-token permutation in the…

Cryptography and Security · Computer Science 2024-04-02 Hengyuan Xu , Liyao Xiang , Hangyu Ye , Dixi Yao , Pengzhi Chu , Baochun Li

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism.…

Computation and Language · Computer Science 2023-08-03 Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N. Gomez , Lukasz Kaiser , Illia Polosukhin

Transformers are a widespread and successful model architecture, particularly in Natural Language Processing (NLP) and Computer Vision (CV). The essential innovation of this architecture is the Attention Mechanism, which solves the problem…

Machine Learning · Computer Science 2024-11-25 Bernhard Bermeitinger , Tomas Hrycej , Massimo Pavone , Julianus Kath , Siegfried Handschuh

Recently, Transformer-based image restoration networks have achieved promising improvements over convolutional neural networks due to parameter-independent global interactions. To lower computational cost, existing works generally limit…

Computer Vision and Pattern Recognition · Computer Science 2023-02-06 Jiale Zhang , Yulun Zhang , Jinjin Gu , Yongbing Zhang , Linghe Kong , Xin Yuan

We study the power of cross-attention in the Transformer architecture within the context of transfer learning for machine translation, and extend the findings of studies into cross-attention when training from scratch. We conduct a series…

Computation and Language · Computer Science 2021-09-15 Mozhdeh Gheini , Xiang Ren , Jonathan May

We conducted empirical experiments to assess the transferability of a light curve transformer to datasets with different cadences and magnitude distributions using various positional encodings (PEs). We proposed a new approach to…

The Transformer is an extremely powerful and prominent deep learning architecture. In this work, we challenge the commonly held belief in deep learning that going deeper is better, and show an alternative design approach that is building…

Machine Learning · Computer Science 2022-11-10 Jason Ross Brown , Yiren Zhao , Ilia Shumailov , Robert D Mullins

The translation equivariance of convolutions can make convolutional neural networks translation equivariant or invariant. Equivariance to other transformations (e.g. rotations, affine transformations, scalings) may also be desirable as soon…

Signal Processing · Electrical Eng. & Systems 2021-05-05 Mateus Sangalli , Samy Blusseau , Santiago Velasco-Forero , Jesus Angulo

Currently, convolutional neural networks (CNN) (e.g., U-Net) have become the de facto standard and attained immense success in medical image segmentation. However, as a downside, CNN based methods are a double-edged sword as they fail to…

Image and Video Processing · Electrical Eng. & Systems 2022-04-01 Reza Azad , Moein Heidari , Yuli Wu , Dorit Merhof

This work proposes an extensive analysis of the Transformer architecture in the Neural Machine Translation (NMT) setting. Focusing on the encoder-decoder attention mechanism, we prove that attention weights systematically make alignment…

Computation and Language · Computer Science 2021-09-14 Javier Ferrando , Marta R. Costa-jussà