paper-with-me

Papers

What Dense Graph Do You Need for Self-Attention?

2022-05-27 · Yuxin Wang, Chu-Tak Lee, Qipeng Guo, Zhangyue Yin, Yunhua Zhou, Xuanjing Huang, Xipeng Qiu

Transformers have made progress in miscellaneous tasks, but suffer from quadratic computational and memory complexities. Recent works propose sparse Transformers with attention on sparse graphs to reduce complexity and remain strong performance. While effective, the crucial parts of how dense a graph needs to be to perform well are not fully explored. In this paper, we propose Normalized Information Payload (NIP), a graph scoring function measuring information transfer on graph, which provides an analysis tool for trade-offs between performance and complexity. Guided by this theoretical analysis, we present Hypercube Transformer, a sparse Transformer that models token interactions in a hypercube and shows comparable or even better results with vanilla Transformer while yielding $O(N\log N)$ complexity with sequence length $N$. Experiments on tasks requiring various sequence lengths lay validation for our graph function well.

📄 PDF Abstract BibTeX arXiv:2205.14014

Code (1)

yxzwang/normalized-information-payload 공식 구현 pytorch

Tasks

Miscellaneous

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
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…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…

Similar Papers 제목 키워드 기반

Faster Attention Is What You Need: A Fast Self-Attention Neural Network Backbone Architecture for the Edge via Double-Condensing Attention Condensers

2022-08-15 · Alexander Wong, Mohammad Javad Shafiee, Saad Abbasi, Saeejith Nair 외

With the growing adoption of deep learning for on-device TinyML applications, there has been an ever-increasing demand for efficient neural network backbones optimized for the edge. Recently, the introduction of attentio…

Efficient Neural Network

How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision

2022-04-11 · ICLR 2021 1 · Dongkwan Kim, Alice Oh

Attention mechanism in graph neural networks is designed to assign larger weights to important neighbor nodes for better representation. However, what graph attention learns is not understood well, particularly when grap…

Graph Attention

The Information Pathways Hypothesis: Transformers are Dynamic Self-Ensembles

2023-06-02 · Md Shamim Hussain, Mohammed J. Zaki, Dharmashankar Subramanian

Transformers use the dense self-attention mechanism which gives a lot of flexibility for long-range connectivity. Over multiple layers of a deep transformer, the number of possible connectivity patterns increases exponen…

Graph LearningGraph RegressionImage ClassificationImage Generation+1

What Makes for Hierarchical Vision Transformer?

2021-07-05 · Yuxin Fang, Xinggang Wang, Rui Wu, Wenyu Liu

Recent studies indicate that hierarchical Vision Transformer with a macro architecture of interleaved non-overlapped window-based self-attention \& shifted-window operation is able to achieve state-of-the-art performance…

Instance Segmentationobject-detectionObject DetectionSemantic Segmentation+1

Is Attention All What You Need? -- An Empirical Investigation on Convolution-Based Active Memory and Self-Attention

2019-12-27 · Thomas Dowdell, Hongyu Zhang

The key to a Transformer model is the self-attention mechanism, which allows the model to analyze an entire sequence in a computationally efficient manner. Recent work has suggested the possibility that general attention…

AllLanguage Modelling