English
Related papers

Related papers: Measuring Affinity between Attention-Head Weight S…

200 papers

The Transformer architecture has achieved tremendous success in natural language processing, computer vision, and scientific computing through its self-attention mechanism. However, its core components-positional encoding and attention…

Machine Learning · Computer Science 2025-11-13 Xianshuai Shi , Jianfeng Zhu , Leibo Liu

Word embedding, which refers to low-dimensional dense vector representations of natural words, has demonstrated its power in many natural language processing tasks. However, it may suffer from the inaccurate and incomplete information…

Computation and Language · Computer Science 2015-06-16 Fei Tian , Bin Gao , Enhong Chen , Tie-Yan Liu

Data-driven approximations of the infinite-dimensional Koopman operator rely on finite-dimensional projections, where the predictive accuracy of the resulting models hinges heavily on the invariance of the chosen subspace. Subspace pruning…

Systems and Control · Electrical Eng. & Systems 2026-04-03 Dhruv Shah , Jorge Cortes

There is a growing interest in the ability of neural networks to execute algorithmic tasks (e.g., arithmetic, summary statistics, and sorting). The goal of this work is to better understand the role of attention in Transformers for…

Machine Learning · Computer Science 2025-06-11 Artur Back de Luca , George Giapitzakis , Shenghao Yang , Petar Veličković , Kimon Fountoulakis

We propose a kernel-based partial permutation test for checking the equality of functional relationship between response and covariates among different groups. The main idea, which is intuitive and easy to implement, is to keep the…

Methodology · Statistics 2021-11-01 Xinran Li , Bo Jiang , Jun S. Liu

We conduct a systematic study of the approximation properties of Transformer for sequence modeling with long, sparse and complicated memory. We investigate the mechanisms through which different components of Transformer, such as the…

Machine Learning · Computer Science 2024-10-31 Mingze Wang , Weinan E

Following the success of dot-product attention in Transformers, numerous approximations have been recently proposed to address its quadratic complexity with respect to the input length. While these variants are memory and compute efficient,…

Computation and Language · Computer Science 2021-06-15 Ankit Gupta , Guy Dar , Shaya Goodman , David Ciprut , Jonathan Berant

Mechanistic interpretability of transformers requires identifying not just which components matter but how they compose into the computational route that produced a prediction. Both attention and MLP follow a shared key-value template…

Machine Learning · Computer Science 2026-05-25 Po-Kai Chen , Niki van Stein , Aske Plaat

A high-performing object detection system plays a crucial role in autonomous driving (AD). The performance, typically evaluated in terms of mean Average Precision, does not take into account orientation and distance of the actors in the…

Computer Vision and Pattern Recognition · Computer Science 2021-07-14 Yiluan Guo , Holger Caesar , Oscar Beijbom , Jonah Philion , Sanja Fidler

Let L be a holomorphic line bundle over a compact complex projective Hermitian manifold X. Any fixed smooth hermitian metric h on L induces a Hilbert space structure on the space of global holomorphic sections with values in the k th tensor…

Complex Variables · Mathematics 2007-12-25 Robert Berman

Trained attention layers exhibit striking and reproducible spectral structure of the weights, including low-rank collapse, bulk deformation, and isolated spectral outliers, yet the origin of these phenomena and their implications for…

Can neural networks learn to compare graphs without feature engineering? In this paper, we show that it is possible to learn representations for graph similarity with neither domain knowledge nor supervision (i.e.\ feature engineering or…

Machine Learning · Computer Science 2019-04-23 Rami Al-Rfou , Dustin Zelle , Bryan Perozzi

While originally designed for natural language processing tasks, the self-attention mechanism has recently taken various computer vision areas by storm. However, the 2D nature of images brings three challenges for applying self-attention in…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Meng-Hao Guo , Cheng-Ze Lu , Zheng-Ning Liu , Ming-Ming Cheng , Shi-Min Hu

Local features at neighboring spatial positions in feature maps have high correlation since their receptive fields are often overlapped. Self-attention usually uses the weighted sum (or other functions) with internal elements of each local…

Computer Vision and Pattern Recognition · Computer Science 2018-08-06 Yang Du , Chunfeng Yuan , Bing Li , Lili Zhao , Yangxi Li , Weiming Hu

Density estimation in high-dimensional settings is an important and challenging statistical problem.Traditional methods based on kernel smoothing are inefficient in high dimensions due to the difficulties in specifying appropriate…

Machine Learning · Statistics 2026-05-14 Ruitong Zhang , Ke Deng

Subgraph isomorphism counting is known as #P-complete and requires exponential time to find the accurate solution. Utilizing representation learning has been shown as a promising direction to represent substructures and approximate the…

Machine Learning · Computer Science 2024-05-14 Xin Liu , Weiqi Wang , Jiaxin Bai , Yangqiu Song

We describe an efficient hierarchical method to compute attention in the Transformer architecture. The proposed attention mechanism exploits a matrix structure similar to the Hierarchical Matrix (H-Matrix) developed by the numerical…

Machine Learning · Computer Science 2021-07-27 Zhenhai Zhu , Radu Soricut

Attention-based models have been a key element of many recent breakthroughs in deep learning. Two key components of Attention are the structure of its input (which consists of keys, values and queries) and the computations by which these…

Machine Learning · Computer Science 2023-05-18 Marta Garnelo , Wojciech Marian Czarnecki

Visual Autoregressive (VAR) models adopt a next-scale prediction paradigm, offering high-quality content generation with substantially fewer decoding steps. However, existing VAR models suffer from significant attention complexity and…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Ziran Qin , Youru Lv , Mingbao Lin , Hang Guo , Zeren Zhang , Danping Zou , Weiyao Lin

While the great capability of Transformers significantly boosts prediction accuracy, it could also yield overconfident predictions and require calibrated uncertainty estimation, which can be commonly tackled by Gaussian processes (GPs).…

Machine Learning · Computer Science 2024-05-29 Yingyi Chen , Qinghua Tao , Francesco Tonin , Johan A. K. Suykens
‹ Prev 1 8 9 10 Next ›