English
Related papers

Related papers: One Wide Feedforward is All You Need

200 papers

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

The paradigm of Transformers using the self-attention mechanism has manifested its advantage in learning graph-structured data. Yet, Graph Transformers are capable of modeling full range dependencies but are often deficient in extracting…

Machine Learning · Computer Science 2024-09-11 Minhong Zhu , Zhenhao Zhao , Weiran Cai

The recent boom of linear forecasting models questions the ongoing passion for architectural modifications of Transformer-based forecasters. These forecasters leverage Transformers to model the global dependencies over temporal tokens of…

Machine Learning · Computer Science 2024-03-15 Yong Liu , Tengge Hu , Haoran Zhang , Haixu Wu , Shiyu Wang , Lintao Ma , Mingsheng Long

Next to scaling considerations, architectural design choices profoundly shape the solution space of transformers. In this work, we analyze the solutions simple transformer blocks implement when tackling the histogram task: counting items in…

Machine Learning · Computer Science 2025-11-13 Freya Behrens , Luca Biggio , Lenka Zdeborová

The large number of parameters in Pretrained Language Models enhance their performance, but also make them resource-intensive, making it challenging to deploy them on commodity hardware like a single GPU. Due to the memory and power…

Computation and Language · Computer Science 2024-01-09 Zirui Liu , Qingquan Song , Qiang Charles Xiao , Sathiya Keerthi Selvaraj , Rahul Mazumder , Aman Gupta , Xia Hu

In this paper, we share our reflections and insights on understanding Transformer architectures through the lens of associative memory--a classic psychological concept inspired by human cognition. We start with the basics of associative…

Machine Learning · Computer Science 2025-05-27 Shu Zhong , Mingyu Xu , Tenglong Ao , Guang Shi

Transformer networks have lead to important progress in language modeling and machine translation. These models include two consecutive modules, a feed-forward layer and a self-attention layer. The latter allows the network to capture long…

Machine Learning · Computer Science 2019-07-03 Sainbayar Sukhbaatar , Edouard Grave , Guillaume Lample , Herve Jegou , Armand Joulin

Feed-forward layers constitute two-thirds of a transformer model's parameters, yet their role in the network remains under-explored. We show that feed-forward layers in transformer-based language models operate as key-value memories, where…

Computation and Language · Computer Science 2021-09-07 Mor Geva , Roei Schuster , Jonathan Berant , Omer Levy

Transformer is an attention-based neural network, which consists of two sublayers, namely, Self-Attention Network (SAN) and Feed-Forward Network (FFN). Existing research explores to enhance the two sublayers separately to improve the…

Computation and Language · Computer Science 2021-03-26 Zhihao Fan , Yeyun Gong , Dayiheng Liu , Zhongyu Wei , Siyuan Wang , Jian Jiao , Nan Duan , Ruofei Zhang , Xuanjing Huang

Network embedding represents nodes in a continuous vector space and preserves structure information from the Network. Existing methods usually adopt a "one-size-fits-all" approach when concerning multi-scale structure information, such as…

Machine Learning · Computer Science 2018-03-28 Lei Sang , Min Xu , Shengsheng Qian , Xindong Wu

The feed-forward networks (FFNs) in transformers are recognized as a group of key-value neural memories to restore abstract high-level knowledge. In this work, we conduct an empirical ablation study on updating keys (the 1st layer in the…

Computation and Language · Computer Science 2024-02-20 Zihan Qiu , Zeyu Huang , Youcheng Huang , Jie Fu

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

Machine Learning · Computer Science 2025-07-01 Venmugil Elango

Understanding how transformer components operate in LLMs is important, as it is at the core of recent technological advances in artificial intelligence. In this work, we revisit the challenges associated with interpretability of…

Machine Learning · Computer Science 2026-02-03 Ajay Jaiswal , Lauren Hannah , Han-Byul Kim , Duc Hoang , Arnav Kundu , Mehrdad Farajtabar , Minsik Cho

The Transformer architecture has inarguably revolutionized deep learning, overtaking classical architectures like multi-layer perceptrons (MLPs) and convolutional neural networks (CNNs). At its core, the attention block differs in form and…

Machine Learning · Computer Science 2025-03-18 Weronika Ormaniec , Felix Dangel , Sidak Pal Singh

Deep neural networks are composed of layers of parametrised linear operations intertwined with non linear activations. In basic models, such as the multi-layer perceptron, a linear layer operates on a simple input vector embedding of the…

Machine Learning · Computer Science 2020-03-06 Jean-Marc Andreoli

Transformer is a powerful model for text understanding. However, it is inefficient due to its quadratic complexity to input sequence length. Although there are many methods on Transformer acceleration, they are still either inefficient on…

Computation and Language · Computer Science 2021-09-07 Chuhan Wu , Fangzhao Wu , Tao Qi , Yongfeng Huang , Xing Xie

The Transformer and its variants have been proven to be efficient sequence learners in many different domains. Despite their staggering success, a critical issue has been the enormous number of parameters that must be trained (ranging from…

Machine Learning · Computer Science 2021-10-28 Subhabrata Dutta , Tanya Gautam , Soumen Chakrabarti , Tanmoy Chakraborty

Techniques for feedforward networks (FFNs) and convolutional networks (CNNs) are frequently reused across families, but the relationship between the underlying model classes is rarely made explicit. We introduce a unified node-level…

Machine Learning · Statistics 2026-02-09 Nicolas Ewen , Jairo Diaz-Rodriguez , Kelly Ramsay

We establish connections between the Transformer architecture, originally introduced for natural language processing, and Graph Neural Networks (GNNs) for representation learning on graphs. We show how Transformers can be viewed as message…

Machine Learning · Computer Science 2025-06-30 Chaitanya K. Joshi

Transformer-based models have brought a radical change to neural machine translation. A key feature of the Transformer architecture is the so-called multi-head attention mechanism, which allows the model to focus simultaneously on different…

Computation and Language · Computer Science 2020-10-06 Alessandro Raganato , Yves Scherrer , Jörg Tiedemann