paper-with-me

Papers

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks

2019-07-25 · Lin Zehui, PengFei Liu, Luyao Huang, Junkun Chen, Xipeng Qiu, Xuanjing Huang

Variants dropout methods have been designed for the fully-connected layer, convolutional layer and recurrent layer in neural networks, and shown to be effective to avoid overfitting. As an appealing alternative to recurrent and convolutional layers, the fully-connected self-attention layer surprisingly lacks a specific dropout method. This paper explores the possibility of regularizing the attention weights in Transformers to prevent different contextualized feature vectors from co-adaption. Experiments on a wide range of tasks show that DropAttention can improve performance and reduce overfitting.

📄 PDF Abstract BibTeX arXiv:1907.11065

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Is logical analysis performed by transformers taking place in self-attention or in the fully connected part?

2025-01-20 · Evgeniy Shin, Heinrich Matzinger

Transformers architecture apply self-attention to tokens represented as vectors, before a fully connected (neuronal network) layer. These two parts can be layered many times. Traditionally, self-attention is seen as a me…

Self-Learning

Maximum Entropy Subspace Clustering Network

2020-12-06 · Zhihao Peng, Yuheng Jia, Hui Liu, Junhui Hou 외

Deep subspace clustering networks have attracted much attention in subspace clustering, in which an auto-encoder non-linearly maps the input data into a latent space, and a fully connected layer named self-expressiveness…

Clustering

Modeling Document Interactions for Learning to Rank with Regularized Self-Attention

2020-05-08 · Shuo Sun, Kevin Duh

Learning to rank is an important task that has been successfully deployed in many real-world information retrieval systems. Most existing methods compute relevance judgments of documents independently, without holistical…

Information RetrievalLearning-To-RankRetrieval

INFusion: Diffusion Regularized Implicit Neural Representations for 2D and 3D accelerated MRI reconstruction

2024-06-19 · Yamin Arefeen, Brett Levac, Zach Stoebner, Jonathan Tamir

Implicit Neural Representations (INRs) are a learning-based approach to accelerate Magnetic Resonance Imaging (MRI) acquisitions, particularly in scan-specific settings when only data from the under-sampled scan itself a…

Image ReconstructionMRI Reconstruction

A Lightweight CNN-Transformer Model for Learning Traveling Salesman Problems

2023-05-03 · Minseop Jung, Jaeseung Lee, Jibum Kim

Several studies have attempted to solve traveling salesman problems (TSPs) using various deep learning techniques. Among them, Transformer-based models show state-of-the-art performance even for large-scale Traveling Sal…

GPU