Instituto de Telecomunicações（电信研究所）；Instituto Superior Técnico（高等技术学院）；LUMLIS (Lisbon ELLIS Unit)（里斯本ELLIS单位（LUMLIS））；Unbabel；Informatics Institute, University of Amsterdam（阿姆斯特丹大学信息学院）；Instituto de Sistemas e Robótica（系统与机器人研究所）
André F. T. Martins, António Farinhas, Marcos Treviso, Vlad Niculae, Pedro M. Q. Aguiar, Mário A. T. Figueiredo
备注：
Accepted for spotlight presentation at NeurIPS 2020
Exponential families are widely used in machine learning; they include many distributions in continuous and discrete domains (e.g., Gaussian, Dirichlet, Poisson, and categorical distributions via the softmax transformation). Distributions in each of these families have fixed support. In contrast, for finite domains, there has been recent work on sparse alternatives to softmax (e.g. sparsemax and alpha-entmax), which have varying support, being able to assign zero probability to irrelevant categories. This paper expands that work in two directions: first, we extend alpha-entmax to continuous domains, revealing a link with Tsallis statistics and deformed exponential families. Second, we introduce continuous-domain attention mechanisms, deriving efficient gradient backpropagation algorithms for alpha in {1,2}. Experiments on attention-based text classification, machine translation, and visual question answering illustrate the use of continuous attention in 1D and 2D, showing that it allows attending to time intervals and compact regions.
Unbabel Lda（Unbabel有限公司）；Instituto de Telecomunicações (IT)（电信研究所（IT））；Instituto Superior Técnico（高等技术学院）；Instituto de Engenharia de Sistemas e Computadores (INESC-ID)（系统与计算机工程研究所（INESC-ID））
We propose sparsemax, a new activation function similar to the traditional softmax, but able to output sparse probabilities. After deriving its properties, we show how its Jacobian can be efficiently computed, enabling its use in a network trained with backpropagation. Then, we propose a new smooth and convex loss function which is the sparsemax analogue of the logistic loss. We reveal an unexpected connection between this new loss and the Huber classification loss. We obtain promising empirical results in multi-label classification problems and in attention-based neural networks for natural l…
Cornell University（康奈尔大学）；NTT Communication Science Laboratories（NTT通信科学实验室）
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 interpr…
Stanford University（斯坦福大学）；Google Research（谷歌研究院）；University of Alberta（阿尔伯塔大学）
Transformers provide a class of expressive architectures that are extremely effective for sequence modeling. However, the key limitation of transformers is their quadratic memory and time complexity $\mathcal{O}(L^2)$ with respect to the sequence length in attention layers, which restricts application in extremely long sequences. Most existing approaches leverage sparsity or low-rank assumptions in the attention matrix to reduce cost, but sacrifice expressiveness. Instead, we propose Combiner, which provides full attention capability in each attention head while maintaining low computation and…
University of Amsterdam（阿姆斯特丹大学）；Priberam Labs（Priberam实验室）；Institute of Systems and Robotics（系统与机器人研究所）；LUMLIS (Lisbon ELLIS Unit)（LUMLIS（里斯本ELLIS单元））；Unbabel（Unbabel公司）
Visual attention mechanisms are widely used in multimodal tasks, as visual question answering (VQA). One drawback of softmax-based attention mechanisms is that they assign some probability mass to all image regions, regardless of their adjacency structure and of their relevance to the text. In this paper, to better link the image structure with the text, we replace the traditional softmax attention mechanism with two alternative sparsity-promoting transformations: sparsemax, which is able to select only the relevant regions (assigning zero weight to the rest), and a newly proposed Total-Variat…
SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers
University of Pittsburgh（匹兹堡大学）；University of Arizona（亚利桑那大学）；Tongji University（同济大学）；University of Central Florida（中佛罗里达大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
University of California, Berkeley（加州大学伯克利分校）；Microsoft Research（微软研究院）
Visual attention helps achieve robust perception under noise, corruption, and distribution shifts in human vision, which are areas where modern neural networks still fall short. We present VARS, Visual Attention from Recurrent Sparse reconstruction, a new attention formulation built on two prominent features of the human visual attention mechanism: recurrency and sparsity. Related features are grouped together via recurrent connections between neurons, with salient objects emerging via sparse regularization. VARS adopts an attractor network with recurrent connections that converges toward a st…
Instituto Superior Técnico, University of Lisbon（里斯本大学高等技术学院）；INESC-ID
This paper introduces and evaluates two novel Hierarchical Attention Network models [Yang et al., 2016] - i) Hierarchical Pruned Attention Networks, which remove the irrelevant words and sentences from the classification process in order to reduce potential noise in the document classification accuracy and ii) Hierarchical Sparsemax Attention Networks, which replace the Softmax function used in the attention mechanism with the Sparsemax [Martins and Astudillo, 2016], capable of better handling importance distributions where a lot of words or sentences have very low probabilities. Our empirical…
Georgia Institute of Technology（佐治亚理工学院）；University of Michigan（密歇根大学）
Attention mechanisms take an expectation of a data representation with respect to probability weights. This creates summary statistics that focus on important features. Recently, (Martins et al. 2020, 2021) proposed continuous attention mechanisms, focusing on unimodal attention densities from the exponential and deformed exponential families: the latter has sparse support. (Farinhas et al. 2021) extended this to use Gaussian mixture attention densities, which are a flexible class with dense support. In this paper, we extend this to two general flexible classes: kernel exponential families and…
Department of Electronic Science, Xiamen University（厦门大学电子科学系）
We present a general architecture of deep differentiable forest and its sparse attention mechanism. The differentiable forest has the advantages of both trees and neural networks. Its structure is a simple binary tree, easy to use and understand. It has full differentiability and all variables are learnable parameters. We would train it by the gradient-based optimization method, which shows great power in the training of deep CNN. We find and analyze the attention mechanism in the differentiable forest. That is, each decision depends on only a few important features, and others are irrelevant.…
University of Vienna（维也纳大学）；Amsterdam UMC（阿姆斯特丹大学医学中心）；University of Amsterdam（阿姆斯特丹大学）
Intensive Care in-hospital mortality prediction has various clinical applications. Neural prediction models, especially when capitalising on clinical notes, have been put forward as improvement on currently existing models. However, to be acceptable these models should be performant and transparent. This work studies different attention mechanisms for clinical neural prediction models in terms of their discrimination and calibration. Specifically, we investigate sparse attention as an alternative to dense attention weights in the task of in-hospital mortality prediction from clinical notes. We…
Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches to reduce this complexity focused on attending to local sliding windows or a small set of locations independent of content. Our work proposes to learn dynamic sparse attention patterns that avoid allocating computation and memory to attend to content unrelated to the query of interest. This work builds upon two lines of research: it combines the modeling fl…
School of Informatics, University of Edinburgh（爱丁堡大学信息学院）；ILLC, University of Amsterdam（阿姆斯特丹大学语言、逻辑与计算研究所）；Department of Computational Linguistics, University of Zurich（苏黎世大学计算语言学系）
Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants. In this work, we introduce a novel, simple method for achieving sparsity in attention: we replace the softmax activation with a ReLU, and show that sparsity naturally emerges from such a formulation. Training stability is achieved with layer normalization with either a specialized initialization or an additional gating function. Our model, which we call Rectified Linear Attention (ReLA), is easy to implement and more efficient than…
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 prompted recent research into sparse Transformers that sparsify the connections in the attention layers. While empirically promising for long sequences, fundamental questions remain unanswered: Can sparse Transformers approximate any arbitrary sequence-to-sequence function, similar to their dense counterparts? How does the sparsity pattern and the sparsity level…
Dimensional Collapse in Transformer Attention Outputs: A Challenge for Sparse Dictionary Learning
Shanghai Innovation Institute, Shanghai, China（上海创新研究院）；OpenMOSS Team, School of Computer Science, Fudan University, Shanghai, China（开放MOSS团队，计算机科学学院，复旦大学）
The attention mechanisms of transformers effectively extract pertinent information from the input sequence. However, the quadratic complexity of self-attention w.r.t the sequence length incurs heavy computational and memory burdens, especially for tasks with long sequences. Existing accelerators face performance degradation in these tasks. To this end, we propose SALO to enable hybrid sparse attention mechanisms for long sequences. SALO contains a data scheduler to map hybrid sparse attention patterns onto hardware and a spatial accelerator to perform the efficient attention computation. We sh…
University of California, Santa Barbara（加州大学圣巴巴拉分校）
Transformers are the mainstream of NLP applications and are becoming increasingly popular in other domains such as Computer Vision. Despite the improvements in model quality, the enormous computation costs make Transformers difficult at deployment, especially when the sequence length is large in emerging applications. Processing attention mechanism as the essential component of Transformer is the bottleneck of execution due to the quadratic complexity. Prior art explores sparse patterns in attention to support long sequence modeling, but those pieces of work are on static or fixed patterns. We…
Instituto Superior Técnico & Instituto de Telecomunicações, Universidade de Lisboa, Portugal（里斯本大学理工学院及电信研究所，葡萄牙）；Champalimaud Research, Lisbon, Portugal（Champalimaud研究，葡萄牙里斯本）；TransPerfect, Lisbon, Portugal（TransPerfect，葡萄牙里斯本）；Carnegie Mellon University, Pittsburgh, USA（卡内基梅隆大学，美国匹兹堡）
Hong Kong University of Science and Technology（香港科技大学）；The University of Hong Kong（香港大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Sun Yat-sen University（中山大学）
Transformer-based models are popularly used in natural language processing (NLP). Its core component, self-attention, has aroused widespread interest. To understand the self-attention mechanism, a direct method is to visualize the attention map of a pre-trained model. Based on the patterns observed, a series of efficient Transformers with different sparse attention masks have been proposed. From a theoretical perspective, universal approximability of Transformer-based models is also recently proved. However, the above understanding and analysis of self-attention is based on a pre-trained model…
Stanford University（斯坦福大学）；Adobe Research（Adobe研究院）；University at Buffalo, SUNY（纽约州立大学布法罗分校）
Recent advances in efficient Transformers have exploited either the sparsity or low-rank properties of attention matrices to reduce the computational and memory bottlenecks of modeling long sequences. However, it is still challenging to balance the trade-off between model quality and efficiency to perform a one-size-fits-all approximation for different tasks. To better understand this trade-off, we observe that sparse and low-rank approximations excel in different regimes, determined by the softmax temperature in attention, and sparse + low-rank can outperform each individually. Inspired by th…
Towards Robust Knowledge Tracing Models via k-Sparse Attention
Think Academy International Education（学而思国际教育）；TAL Education Group（好未来教育集团）；Guangdong Institute of Smart Education（广东省智慧教育研究院）；Jinan University（暨南大学）；City University of Hong Kong（香港城市大学）；College of Cyber Security（网络空间安全学院）
University of California, Santa Barbara（加州大学圣巴巴拉分校）；ALIBABA DAMO Academy（阿里巴巴达摩院）
Transformers are becoming the mainstream solutions for various tasks like NLP and Computer vision. Despite their success, the high complexity of the attention mechanism hinders them from being applied to latency-sensitive tasks. Tremendous efforts have been made to alleviate this problem, and many of them successfully reduce the asymptotic complexity to linear. Nevertheless, most of them fail to achieve practical speedup over the original full attention under moderate sequence lengths and are unfriendly to finetuning. In this paper, we present DFSS, an attention mechanism that dynamically prun…
Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of irrelevant information in the context. To tackle the problem, we propose a novel model called \textbf{Explicit Sparse Transformer}. Explicit Sparse Transformer is able to improve the concentration of attention on the global context through an explicit selection of the most relevant segments. Extensive experimental results on a series of natural language processing an…
How Sparse Attention Approximates Exact Attention? Your Attention is Naturally $n^C$-Sparse
The University of Washington（华盛顿大学）；Simons Institute for the Theory of Computing, University of California, Berkeley（加州大学伯克利分校西蒙斯理论计算研究所）；The University of Hong Kong（香港大学）；Sun Yat-sen University（中山大学）
We propose Sparse Sinkhorn Attention, a new efficient and sparse method for learning to attend. Our method is based on differentiable sorting of internal representations. Concretely, we introduce a meta sorting network that learns to generate latent permutations over sequences. Given sorted sequences, we are then able to compute quasi-global attention with only local windows, improving the memory efficiency of the attention module. To this end, we propose new algorithmic innovations such as Causal Sinkhorn Balancing and SortCut, a dynamic sequence truncation method for tailoring Sinkhorn Atten…
