English
Related papers

Related papers: Attention-Only Transformers via Unrolled Subspace …

200 papers

In this paper, we contend that the objective of representation learning is to compress and transform the distribution of the data, say sets of tokens, towards a mixture of low-dimensional Gaussian distributions supported on incoherent…

Machine Learning · Computer Science 2023-06-05 Yaodong Yu , Sam Buchanan , Druv Pai , Tianzhe Chu , Ziyang Wu , Shengbang Tong , Benjamin D. Haeffele , Yi Ma

The self-attention mechanism, a cornerstone of Transformer-based state-of-the-art deep learning architectures, is largely heuristic-driven and fundamentally challenging to interpret. Establishing a robust theoretical foundation to explain…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Laziz U. Abdullaev , Maksim Tkachenko , Tan M. Nguyen

Transformers serve as the foundational architecture for large language and video generation models, such as GPT, BERT, SORA and their successors. Empirical studies have demonstrated that real-world data and learning tasks exhibit…

Machine Learning · Computer Science 2026-05-19 Zhaiming Shen , Alex Havrilla , Rongjie Lai , Alexander Cloninger , Wenjing Liao

In this paper, we contend that a natural objective of representation learning is to compress and transform the distribution of the data, say sets of tokens, towards a low-dimensional Gaussian mixture supported on incoherent subspaces. The…

Machine Learning · Computer Science 2024-09-09 Yaodong Yu , Sam Buchanan , Druv Pai , Tianzhe Chu , Ziyang Wu , Shengbang Tong , Hao Bai , Yuexiang Zhai , Benjamin D. Haeffele , Yi Ma

Unlike conventional "black-box" transformers with classical self-attention mechanism, we build a lightweight and interpretable transformer-like neural net by unrolling a mixed-graph-based optimization algorithm to forecast traffic with…

Machine Learning · Computer Science 2026-02-04 Ji Qi , Tam Thuc Do , Mingxiao Liu , Zhuoshi Pan , Yuzhe Li , Gene Cheung , H. Vicky Zhao

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

Deep unrolling, or unfolding, is an emerging learning-to-optimize method that unrolls a truncated iterative algorithm in the layers of a trainable neural network. However, the convergence guarantees and generalizability of the unrolled…

Machine Learning · Computer Science 2024-12-02 Samar Hadou , Navid NaderiAlizadeh , Alejandro Ribeiro

Transformers have achieved remarkable success in a wide range of natural language processing and computer vision applications. However, the representation capacity of a deep transformer model is degraded due to the over-smoothing issue in…

Computation and Language · Computer Science 2023-12-04 Tam Nguyen , Tan M. Nguyen , Richard G. Baraniuk

We build interpretable and lightweight transformer-like neural networks by unrolling iterative optimization algorithms that minimize graph smoothness priors -- the quadratic graph Laplacian regularizer (GLR) and the $\ell_1$-norm graph…

Machine Learning · Computer Science 2024-11-07 Tam Thuc Do , Parham Eftekhar , Seyed Alireza Hosseini , Gene Cheung , Philip Chou

Transformer is beneficial for image denoising tasks since it can model long-range dependencies to overcome the limitations presented by inductive convolutional biases. However, directly applying the transformer structure to remove noise is…

Computer Vision and Pattern Recognition · Computer Science 2023-04-14 Kangliang Liu , Xiangcheng Du , Sijie Liu , Yingbin Zheng , Xingjiao Wu , Cheng Jin

Deep learning based methods hold state-of-the-art results in low-level image processing tasks, but remain difficult to interpret due to their black-box construction. Unrolled optimization networks present an interpretable alternative to…

Image and Video Processing · Electrical Eng. & Systems 2025-11-18 Nikola Janjušević , Amirhossein Khalilian-Gourtani , Yao Wang

Self-attention mechanism is the key of the Transformer but often criticized for its computation demands. Previous token pruning works motivate their methods from the view of computation redundancy but still need to load the full network and…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Sihao Lin , Pumeng Lyu , Dongrui Liu , Tao Tang , Xiaodan Liang , Andy Song , Xiaojun Chang

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

We propose an interpretable graph neural network framework to denoise single or multiple noisy graph signals. The proposed graph unrolling networks expand algorithm unrolling to the graph domain and provide an interpretation of the…

Signal Processing · Electrical Eng. & Systems 2021-09-08 Siheng Chen , Yonina C. Eldar , Lingxiao Zhao

Point clouds obtained from capture devices or 3D reconstruction techniques are often noisy and interfere with downstream tasks. The paper aims to recover the underlying surface of noisy point clouds. We design a novel model, NoiseTrans,…

Computer Vision and Pattern Recognition · Computer Science 2023-04-25 Guangzhe Hou , Guihe Qin , Minghui Sun , Yanhua Liang , Jie Yan , Zhonghan Zhang

Transformer-based deep learning models have achieved state-of-the-art performance across numerous language and vision tasks. While the self-attention mechanism, a core component of transformers, has proven capable of handling complex data…

Machine Learning · Computer Science 2025-08-05 Laziz Abdullaev , Tan M. Nguyen

The extraction of geoelectric structural information from airborne transient electromagnetic(ATEM)data primarily involves data processing and inversion. Conventional methods rely on empirical parameter selection, making it difficult to…

Machine Learning · Computer Science 2025-03-31 Shuang Wang , Xuben Wang , Fei Deng , Xiaodong Yu , Peifan Jiang , Lifeng Mao

The Transformer architecture has gained growing attention in graph representation learning recently, as it naturally overcomes several limitations of graph neural networks (GNNs) by avoiding their strict structural inductive biases and…

Machine Learning · Statistics 2022-06-14 Dexiong Chen , Leslie O'Bray , Karsten Borgwardt

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

Deep learning based methods hold state-of-the-art results in image denoising, but remain difficult to interpret due to their construction from poorly understood building blocks such as batch-normalization, residual learning, and feature…

Image and Video Processing · Electrical Eng. & Systems 2021-03-09 Nikola Janjušević , Amirhossein Khalilian-Gourtani , Yao Wang
‹ Prev 1 2 3 10 Next ›