English
Related papers

Related papers: How Smoothing is N-simplicial Attention?

200 papers

Self-attention and masked self-attention are at the heart of Transformers' outstanding success. Still, our mathematical understanding of attention, in particular of its Lipschitz properties - which are key when it comes to analyzing…

Machine Learning · Computer Science 2024-06-05 Valérie Castin , Pierre Ablin , Gabriel Peyré

Recently over-smoothing phenomenon of Transformer-based models is observed in both vision and language fields. However, no existing work has delved deeper to further investigate the main cause of this phenomenon. In this work, we make the…

Machine Learning · Computer Science 2022-02-18 Han Shi , Jiahui Gao , Hang Xu , Xiaodan Liang , Zhenguo Li , Lingpeng Kong , Stephen M. S. Lee , James T. Kwok

Attention is a powerful component of modern neural networks across a wide variety of domains. In this paper, we seek to quantify the regularity (i.e. the amount of smoothness) of the attention operation. To accomplish this goal, we propose…

Machine Learning · Statistics 2021-02-11 James Vuckovic , Aristide Baratin , Remi Tachet des Combes

Recent work in imitation learning has shown that having an expert controller that is both suitably smooth and stable enables stronger guarantees on the performance of the learned controller. However, constructing such smoothed expert…

Systems and Control · Electrical Eng. & Systems 2024-09-04 Daniel Pfrommer , Swati Padmanabhan , Kwangjun Ahn , Jack Umenberger , Tobia Marcucci , Zakaria Mhammedi , Ali Jadbabaie

The self-attention mechanism in transformers and the message-passing mechanism in graph neural networks are repeatedly applied within deep learning architectures. We show that this application inevitably leads to oversmoothing, i.e., to…

Machine Learning · Computer Science 2023-06-05 Ameen Ali , Tomer Galanti , Lior Wolf

Graph transformers achieve strong results on molecular and long-range reasoning tasks, yet remain hampered by over-smoothing (the progressive collapse of node representations with depth) and attention entropy degeneration. We observe that…

Machine Learning · Computer Science 2026-04-21 Dongxin Guo , Jikun Wu , Siu Ming Yiu

Attention-based architectures have become ubiquitous in machine learning, yet our understanding of the reasons for their effectiveness remains limited. This work proposes a new way to understand self-attention networks: we show that their…

Machine Learning · Computer Science 2023-08-02 Yihe Dong , Jean-Baptiste Cordonnier , Andreas Loukas

Due to their ability to model meaningful higher order relations among a set of entities, higher order network models have emerged recently as a powerful alternative for graph-based network models which are only capable of modeling binary…

Machine Learning · Computer Science 2023-12-20 Karthikeyan Natesan Ramamurthy , Aldo Guzmán-Sáenz , Mustafa Hajij

Self-attention mechanism is the key of the Transformer but often criticized for its computation demands. Previous token pruning works motivate their methods from the view of computation redundancy but still need to load the full network and…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Sihao Lin , Pumeng Lyu , Dongrui Liu , Tao Tang , Xiaodan Liang , Andy Song , Xiaojun Chang

In this paper, we propose that the dot product pairwise matching attention layer, which is widely used in Transformer-based models, is redundant for the model performance. Attention, in its original formulation, has to be seen rather as a…

Computation and Language · Computer Science 2022-06-29 Uladzislau Yorsh , Alexander Kovalenko , Vojtěch Vančura , Daniel Vašata , Pavel Kordík , Tomáš Mikolov

Recent work in imitation learning has shown that having an expert controller that is both suitably smooth and stable enables stronger guarantees on the performance of the learned controller. However, constructing such smoothed expert…

Systems and Control · Electrical Eng. & Systems 2024-10-02 Daniel Pfrommer , Swati Padmanabhan , Kwangjun Ahn , Jack Umenberger , Tobia Marcucci , Zakaria Mhammedi , Ali Jadbabaie

Slot Attention (SA) lies at the heart of mainstream Object-Centric Learning (OCL). Image features can be aggregated into object-level representations by SA \textit{iteratively} refining cold-start query slots. For video, such aggregation…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Rongzhen Zhao , Wenyan Yang , Juho Kannala , Joni Pajarinen

Attention based models have achieved many remarkable breakthroughs in numerous applications. However, the quadratic complexity of Attention makes the vanilla Attention based models hard to apply to long sequence tasks. Various improved…

Machine Learning · Computer Science 2024-09-18 Xue Wang , Tian Zhou , Jianqing Zhu , Jialin Liu , Kun Yuan , Tao Yao , Wotao Yin , Rong Jin , HanQin Cai

We study a class of optimization problems on Riemannian manifolds, where the objective function consists of a smooth term and quasi-norm type penalties with exponent $p \in (0, 1]$. The essential difficulty lies in the fact that the…

Optimization and Control · Mathematics 2026-04-21 Lei Wang , Xiaojun Chen

Linear attention mechanisms have emerged as efficient alternatives to full self-attention in Graph Transformers, offering linear time complexity. However, existing linear attention models often suffer from a significant drop in…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Zhaolin Hu , Kun Li , Hehe Fan , Yi Yang

Structured data, which constitutes a significant portion of existing data types, has been a long-standing research topic in the field of machine learning. Various representation learning methods for tabular data have been proposed, ranging…

Artificial Intelligence · Computer Science 2023-12-19 Jayoung Kim , Yehjin Shin , Jeongwhan Choi , Hyowon Wi , Noseong Park

Transformer models typically calculate attention matrices using dot products, which have limitations when capturing nonlinear relationships between embedding vectors. We propose Neural Attention, a technique that replaces dot products with…

Machine Learning · Computer Science 2025-11-10 Andrew DiGiugno , Ausif Mahmood

Attention is a powerful component of modern neural networks across a wide variety of domains. However, despite its ubiquity in machine learning, there is a gap in our understanding of attention from a theoretical point of view. We propose a…

Machine Learning · Statistics 2020-07-21 James Vuckovic , Aristide Baratin , Remi Tachet des Combes

The empirical success of Reinforcement Learning (RL) in the setting of contact-rich manipulation leaves much to be understood from a model-based perspective, where the key difficulties are often attributed to (i) the explosion of contact…

Robotics · Computer Science 2023-03-01 Tao Pang , H. J. Terry Suh , Lujie Yang , Russ Tedrake

Randomized smoothing is a widely adopted technique for optimizing nonsmooth objective functions. However, its efficiency analysis typically relies on global Lipschitz continuity, a condition rarely met in practical applications. To address…

Optimization and Control · Mathematics 2025-09-10 Jingfan Xia , Zhenwei Lin , Qi Deng
‹ Prev 1 2 3 10 Next ›