English
Related papers

Related papers: Transformers Provably Learn Sparse Token Selection…

200 papers

We investigate the use of sparse coding and dictionary learning in the context of multitask and transfer learning. The central assumption of our learning method is that the tasks parameters are well approximated by sparse linear…

Machine Learning · Computer Science 2014-06-17 Andreas Maurer , Massimiliano Pontil , Bernardino Romera-Paredes

Deep learning has achieved remarkable success in modeling sequential data, including event sequences, temporal point processes, and irregular time series. Recently, transformers have largely replaced recurrent networks in these tasks.…

Machine Learning · Computer Science 2025-08-05 Ivan Karpukhin , Andrey Savchenko

A fundamental task for artificial intelligence is learning. Deep Neural Networks have proven to cope perfectly with all learning paradigms, i.e. supervised, unsupervised, and reinforcement learning. Nevertheless, traditional deep learning…

Artificial Intelligence · Computer Science 2021-03-03 Decebal Constantin Mocanu , Elena Mocanu , Tiago Pinto , Selima Curci , Phuong H. Nguyen , Madeleine Gibescu , Damien Ernst , Zita A. Vale

Graph convolutional networks (GCNs) have recently achieved great empirical success in learning graph-structured data. To address its scalability issue due to the recursive embedding of neighboring features, graph topology sampling has been…

Machine Learning · Computer Science 2023-12-12 Hongkang Li , Meng Wang , Sijia Liu , Pin-Yu Chen , Jinjun Xiong

Neural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without compromising accuracy. However, contemporary…

Machine Learning · Computer Science 2019-03-05 Jonathan Frankle , Michael Carbin

Large transformer-based language models have been shown to be very effective in many classification tasks. However, their computational complexity prevents their use in applications requiring the classification of a large set of candidates.…

Computation and Language · Computer Science 2020-05-08 Luca Soldaini , Alessandro Moschitti

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

Empirical studies have identified a range of learnability biases and limitations of transformers, such as a persistent difficulty in learning to compute simple formal languages such as PARITY, and a bias towards low-degree functions.…

Machine Learning · Computer Science 2024-05-28 Michael Hahn , Mark Rofin

Many approaches to transform classification problems from non-linear to linear by feature transformation have been recently presented in the literature. These notably include sparse coding methods and deep neural networks. However, many of…

Machine Learning · Computer Science 2015-07-08 Alessandro Montalto , Giovanni Tessitore , Roberto Prevete

Recently, Transformer networks have redefined the state of the art in many NLP tasks. However, these models suffer from quadratic computational cost in the input sequence length $n$ to compute pairwise attention in each layer. This has…

Machine Learning · Computer Science 2020-12-22 Chulhee Yun , Yin-Wen Chang , Srinadh Bhojanapalli , Ankit Singh Rawat , Sashank J. Reddi , Sanjiv Kumar

Transformer has achieved great success in NLP. However, the quadratic complexity of the self-attention mechanism in Transformer makes it inefficient in handling long sequences. Many existing works explore to accelerate Transformers by…

Computation and Language · Computer Science 2021-09-03 Chuhan Wu , Fangzhao Wu , Tao Qi , Binxing Jiao , Daxin Jiang , Yongfeng Huang , Xing Xie

Transformer architecture has become the de-facto model for many machine learning tasks from natural language processing and computer vision. As such, improving its computational efficiency becomes paramount. One of the major computational…

Computation and Language · Computer Science 2022-05-17 Yue Guan , Zhengyi Li , Jingwen Leng , Zhouhan Lin , Minyi Guo

Transformers perform inference by iteratively transforming token representations across layers. This layerwise computation has been studied empirically, and recent mean-field theories of Transformer dynamics explain how attention can drive…

Machine Learning · Computer Science 2026-05-11 Noboru Isobe , Daisuke Inoue , Masaaki Imaizumi

When training data are limited, data-driven models are especially vulnerable to optimization-related fluctuations from random initialization and to sampling-induced bias from insufficient training data. We address both challenges with…

Nuclear Theory · Physics 2026-03-31 Yinu Zhang , Zhiyi Li , Kele Li , Jiaxuan Zhong , Cenxi Yuan

While transformers have proven enormously successful in a range of tasks, their fundamental properties as models of computation are not well understood. This paper contributes to the study of the expressive capacity of transformers,…

Machine Learning · Computer Science 2025-03-31 Lena Strobl , Dana Angluin , Robert Frank

Lottery Ticket Hypothesis (LTH) suggests that a dense neural network contains a sparse sub-network that can match the performance of the original dense network when trained in isolation from scratch. Most works retrain the sparse…

Machine Learning · Computer Science 2021-10-12 Ajay Kumar Jaiswal , Haoyu Ma , Tianlong Chen , Ying Ding , Zhangyang Wang

This paper proposes a transformer over transformer framework, called Transformer$^2$, to perform neural text segmentation. It consists of two components: bottom-level sentence encoders using pre-trained transformers, and an upper-level…

Computation and Language · Computer Science 2021-10-15 Kelvin Lo , Yuan Jin , Weicong Tan , Ming Liu , Lan Du , Wray Buntine

Graph Transformers, which incorporate self-attention and positional encoding, have recently emerged as a powerful architecture for various graph learning tasks. Despite their impressive performance, the complex non-convex interactions…

Machine Learning · Computer Science 2024-06-05 Hongkang Li , Meng Wang , Tengfei Ma , Sijia Liu , Zaixi Zhang , Pin-Yu Chen

The video action segmentation task is regularly explored under weaker forms of supervision, such as transcript supervision, where a list of actions is easier to obtain than dense frame-wise labels. In this formulation, the task presents…

Computer Vision and Pattern Recognition · Computer Science 2022-01-24 John Ridley , Huseyin Coskun , David Joseph Tan , Nassir Navab , Federico Tombari

The Lottery Ticket Hypothesis suggests large, over-parameterized neural networks consist of small, sparse subnetworks that can be trained in isolation to reach a similar (or better) test accuracy. However, the initialization and…

Computation and Language · Computer Science 2019-10-29 Shrey Desai , Hongyuan Zhan , Ahmed Aly