most citedUnmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights

1 citations · 1 across the 3 of their papers we have counts for

collaborators

5 papers

cs.LG2024

How Sparse Attention Approximates Exact Attention? Your Attention is Naturally -Sparse

Yichuan Deng, Zhao Song, Jing Xiong +1

Sparse Attention is a technique that approximates standard attention computation with sub-quadratic complexity. This is achieved by selectively ignoring smaller entries in the atte…

cs.LG2024

Enhancing Stochastic Gradient Descent: A Unified Framework and Novel Acceleration Methods for Faster Convergence

Yichuan Deng, Zhao Song, Chiwun Yang

Based on SGD, previous works have proposed many algorithms that have improved convergence speed and generalization in stochastic optimization, such as SGDm, AdaGrad, Adam, etc. How…

cs.CV2023

Image change detection with only a few samples

Ke Liu, Zhaoyi Song, Haoyue Bai

This paper considers image change detection with only a small number of samples, which is a significant problem in terms of a few annotations available. A major impediment of image…

cs.LG20231 cited

Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights

Yichuan Deng, Zhao Song, Shenghao Xie +1

In the realm of deep learning, transformers have emerged as a dominant architecture, particularly in natural language processing tasks. However, with their widespread adoption, con…

cs.CL2023

Why Softmax Attention Outperforms Linear Attention

Yichuan Deng, Zhao Song, Kaijun Yuan +1

Large transformer models have achieved state-of-the-art results in numerous natural language processing tasks. Among the pivotal components of the transformer architecture, the att…