paper-with-me

Papers

A Regularized Framework for Sparse and Structured Neural Attention

2017-05-22 · NeurIPS 2017 12 · Vlad Niculae, Mathieu Blondel

Modern neural networks are often augmented with an attention mechanism, which tells the network where to focus within the input. We propose in this paper a new framework for sparse and structured attention, building upon a smoothed max operator. We show that the gradient of this operator defines a mapping from real values to probabilities, suitable as an attention mechanism. Our framework includes softmax and a slight generalization of the recently-proposed sparsemax as special cases. However, we also show how our framework can incorporate modern structured penalties, resulting in more interpretable attention mechanisms, that focus on entire segments or groups of an input. We derive efficient algorithms to compute the forward and backward passes of our attention mechanisms, enabling their use in a neural network trained with backpropagation. To showcase their potential as a drop-in replacement for existing ones, we evaluate our attention mechanisms on three large-scale tasks: textual entailment, machine translation, and sentence summarization. Our attention mechanisms improve interpretability without sacrificing performance; notably, on textual entailment and summarization, we outperform the standard attention mechanisms based on softmax and sparsemax.

📄 PDF Abstract BibTeX arXiv:1705.07704

Code (3)

dhruvdcoder/sparse-structured-attention pytorch
vene/sparse-structured-attention pytorch
weiwang2330/sparse-structured-attention pytorch

Tasks

Machine TranslationNatural Language InferenceSentenceSentence SummarizationText SummarizationTranslation

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

ARAC: Adaptive Regularized Multi-Agent Soft Actor-Critic in Graph-Structured Adversarial Games

2025-11-11 · Ruochuan Shi, Runyu Lu, Yuanheng Zhu, Dongbin Zhao arxiv

In graph-structured multi-agent reinforcement learning (MARL) adversarial tasks such as pursuit and confrontation, agents must coordinate under highly dynamic interactions, where sparse rewards hinder efficient policy le…

Multi-agent Reinforcement LearningGraph Neural Network

Structured Sparse Method for Hyperspectral Unmixing

2014-03-19 · Feiyun Zhu, Ying Wang, Shiming Xiang, Bin Fan 외

Hyperspectral Unmixing (HU) has received increasing attention in the past decades due to its ability of unveiling information latent in hyperspectral data. Unfortunately, most existing methods fail to take advantage of t…

Hyperspectral Unmixing

A Unified Framework for Solving a General Class of Nonconvexly Regularized Convex Models

2023-06-26 · Yi Zhang, Isao Yamada

Recently, several nonconvex sparse regularizers which can preserve the convexity of the cost function have received increasing attention. This paper proposes a general class of such convexity-preserving (CP) regularizers…

A unified framework for high-dimensional analysis of M-estimators with decomposable regularizers

2009-12-01 · NeurIPS 2009 12 · Sahand Negahban, Bin Yu, Martin J. Wainwright, Pradeep K. Ravikumar

The estimation of high-dimensional parametric models requires imposing some structure on the models, for instance that they be sparse, or that matrix structured parameters have low rank. A general approach for such struc…

Sparse Graph Attention Networks

2019-12-02 · Yang Ye, Shihao Ji

Graph Neural Networks (GNNs) have proved to be an effective representation learning framework for graph-structured data, and have achieved state-of-the-art performance on many practical predictive tasks, such as node cla…

ClassificationGeneral ClassificationGraph AttentionGraph Classification+4