English
Related papers

Related papers: Simplifying Transformer Blocks

200 papers

Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences. We introduce two techniques to improve the efficiency of…

Machine Learning · Computer Science 2020-02-19 Nikita Kitaev , Łukasz Kaiser , Anselm Levskaya

While scaling Transformer-based large language models (LLMs) has demonstrated promising performance across various tasks, it also introduces redundant architectures, posing efficiency challenges for real-world deployment. Despite some…

Machine Learning · Computer Science 2024-10-18 Shwai He , Guoheng Sun , Zheyu Shen , Ang Li

We present a generalization of Transformers to any-order permutation invariant data (sets, graphs, and hypergraphs). We begin by observing that Transformers generalize DeepSets, or first-order (set-input) permutation invariant MLPs. Then,…

Machine Learning · Computer Science 2022-01-25 Jinwoo Kim , Saeyoon Oh , Seunghoon Hong

In recent developments in the field of Computer Vision, a rise is seen in the use of transformer-based architectures. They are surpassing the state-of-the-art set by CNN architectures in accuracy but on the other hand, they are…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Durvesh Malpure , Onkar Litake , Rajesh Ingle

Multi-task learning (MTL) aims to leverage shared knowledge across tasks to improve generalization and parameter efficiency, yet balancing resources and mitigating interference remain open challenges. Architectural solutions often introduce…

Machine Learning · Computer Science 2025-12-24 Mihai Suteu , Ovidiu Serban

Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer…

Machine Learning · Computer Science 2025-06-05 Peng Wang , Yifu Lu , Yaodong Yu , Druv Pai , Qing Qu , Yi Ma

Overparameterized neural networks generalize well but are expensive to train. Ideally, one would like to reduce their computational cost while retaining their generalization benefits. Sparse model training is a simple and promising approach…

Machine Learning · Computer Science 2022-05-12 Tri Dao , Beidi Chen , Kaizhao Liang , Jiaming Yang , Zhao Song , Atri Rudra , Christopher Ré

The Transformer is widely used in natural language processing tasks. To train a Transformer however, one usually needs a carefully designed learning rate warm-up stage, which is shown to be crucial to the final performance but will slow…

Machine Learning · Computer Science 2020-06-30 Ruibin Xiong , Yunchang Yang , Di He , Kai Zheng , Shuxin Zheng , Chen Xing , Huishuai Zhang , Yanyan Lan , Liwei Wang , Tie-Yan Liu

Despite the widespread success of Transformers on NLP tasks, recent works have found that they struggle to model several formal languages when compared to recurrent models. This raises the question of why Transformers perform well in…

Machine Learning · Computer Science 2023-07-11 Satwik Bhattamishra , Arkil Patel , Varun Kanade , Phil Blunsom

In computer vision and natural language processing, innovations in model architecture that increase model capacity have reliably translated into gains in performance. In stark contrast with this trend, state-of-the-art reinforcement…

Machine Learning · Computer Science 2022-01-05 Johan Bjorck , Carla P. Gomes , Kilian Q. Weinberger

With the proliferation of mobile devices and the Internet of Things, deep learning models are increasingly deployed on devices with limited computing resources and memory, and are exposed to the threat of adversarial noise. Learning deep…

Computer Vision and Pattern Recognition · Computer Science 2021-12-30 Xian Wei , Yanhui Huang , Yangyu Xu , Mingsong Chen , Hai Lan , Yuanxiang Li , Zhongfeng Wang , Xuan Tang

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Machine Learning · Computer Science 2023-03-28 Quentin Fournier , Gaétan Marceau Caron , Daniel Aloise

Transformer has been widely used thanks to its ability to capture sequence information in an efficient way. However, recent developments, such as BERT and GPT-2, deliver only heavy architectures with a focus on effectiveness. In this paper,…

Computation and Language · Computer Science 2020-02-17 Chenguang Wang , Zihao Ye , Aston Zhang , Zheng Zhang , Alexander J. Smola

Although Transformer has achieved great successes on many NLP tasks, its heavy structure with fully-connected attention connections leads to dependencies on large training data. In this paper, we present Star-Transformer, a lightweight…

Computation and Language · Computer Science 2022-04-26 Qipeng Guo , Xipeng Qiu , Pengfei Liu , Yunfan Shao , Xiangyang Xue , Zheng Zhang

Transformers have demonstrated effectiveness in in-context solving data-fitting problems from various (latent) models, as reported by Garg et al. However, the absence of an inherent iterative structure in the transformer architecture…

Machine Learning · Computer Science 2024-03-19 Liu Yang , Kangwook Lee , Robert Nowak , Dimitris Papailiopoulos

Transformer architectures dominate modern NLP but often demand heavy computational resources and intricate hyperparameter tuning. To mitigate these challenges, we propose a novel framework, BoostTransformer, that augments transformers with…

Machine Learning · Computer Science 2025-11-04 Biyi Fang , Truong Vo , Jean Utke , Diego Klabjan

This paper reveals a novel linear characteristic exclusive to transformer decoders, including models such as GPT, LLaMA, OPT, BLOOM and others. We analyze embedding transformations between sequential layers, uncovering a near-perfect linear…

We propose a simple and efficient approach for training the BERT model. Our approach exploits the special structure of BERT that contains a stack of repeated modules (i.e., transformer encoders). Our proposed approach first trains BERT with…

Machine Learning · Computer Science 2021-10-11 Shuo Yang , Le Hou , Xiaodan Song , Qiang Liu , Denny Zhou

Predictive Process Monitoring (PPM) aims to forecast the future behavior of ongoing process instances using historical event data, enabling proactive decision-making. While recent advances rely heavily on deep learning models such as LSTMs…

Machine Learning · Computer Science 2025-09-23 Amaan Ansari , Lukas Kirchdorfer , Raheleh Hadian

Multiple studies have shown that Transformers are remarkably robust to pruning. Contrary to this received wisdom, we demonstrate that pre-trained Transformer encoders are surprisingly fragile to the removal of a very small number of…

Computation and Language · Computer Science 2021-06-04 Olga Kovaleva , Saurabh Kulshreshtha , Anna Rogers , Anna Rumshisky