English
Related papers

Related papers: Grouped Differential Attention

200 papers

Multi-head self-attention forms the core of Transformer networks. However, their quadratically growing complexity with respect to the input sequence length impedes their deployment on resource-constrained edge devices. We address this…

Computation and Language · Computer Science 2022-04-08 Zuzana Jelčicová , Marian Verhelst

Transformers have achieved promising results on a variety of tasks. However, the quadratic complexity in self-attention computation has limited the applications, especially in low-resource settings and mobile or edge devices. Existing works…

Sound · Computer Science 2024-01-09 Wentao Zhu

The dominant paradigm for machine learning on graphs uses Message Passing Graph Neural Networks (MP-GNNs), in which node representations are updated by aggregating information in their local neighborhood. Recently, there have been…

Machine Learning · Computer Science 2023-03-02 Daniel Glickman , Eran Yahav

The escalating overlap between non-geostationary orbit (NGSO) and geostationary orbit (GSO) satellite frequency allocations necessitates accurate interference detection methods that address two pivotal technical gaps: computationally…

Signal Processing · Electrical Eng. & Systems 2025-04-25 Chunyu Yang , Boyu Yang , Kun Qiu , Zhe Chen , Yue Gao

Multi-Head Attention (MHA) is a key component of Transformer. In MHA, attention heads work independently, causing problems such as low-rank bottleneck of attention score matrices and head redundancy. We propose Dynamically Composable…

Machine Learning · Computer Science 2024-06-05 Da Xiao , Qingye Meng , Shengping Li , Xingyuan Yuan

Graph Domain Adaptation (GDA) addresses a pressing challenge in cross-network learning, particularly pertinent due to the absence of labeled data in real-world graph datasets. Recent studies attempted to learn domain invariant…

Machine Learning · Computer Science 2025-02-26 Ruiyi Fang , Bingheng Li , Zhao Kang , Qiuhao Zeng , Nima Hosseini Dashtbayaz , Ruizhi Pu , Boyu Wang , Charles Ling

Although distributed machine learning has opened up many new and exciting research frontiers, fragmentation of models and data across different machines, nodes, and sites still results in considerable communication overhead, impeding…

Machine Learning · Computer Science 2022-02-04 Bradley T. Baker , Aashis Khanal , Vince D. Calhoun , Barak Pearlmutter , Sergey M. Plis

Impressive performance of Transformer has been attributed to self-attention, where dependencies between entire input in a sequence are considered at every position. In this work, we reform the neural $n$-gram model, which focuses on only…

Computation and Language · Computer Science 2022-07-28 Mengsay Loem , Sho Takase , Masahiro Kaneko , Naoaki Okazaki

Diffusion-based Transformers have demonstrated impressive generative capabilities, but their high computational costs hinder practical deployment, for example, generating an $8192\times 8192$ image can take over an hour on an A100 GPU. In…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Sucheng Ren , Qihang Yu , Ju He , Alan Yuille , Liang-Chieh Chen

Relational reasoning is a central component of generally intelligent systems, enabling robust and data-efficient inductive generalization. Recent empirical evidence shows that many existing neural architectures, including Transformers,…

Machine Learning · Computer Science 2025-06-23 Awni Altabaa , John Lafferty

We introduce Robust Filter Attention (RFA), a formulation of self-attention as a robust state estimator. Each token is treated as a noisy observation of a latent trajectory governed by a linear stochastic differential equation (SDE), and…

Machine Learning · Computer Science 2026-05-26 Peter Racioppo

This paper introduces a novel attention mechanism, called dual attention, which is both efficient and effective. The dual attention mechanism consists of two parallel components: local attention generated by Convolutional Neural Networks…

Computer Vision and Pattern Recognition · Computer Science 2023-05-25 Zhengkai Jiang , Liang Liu , Jiangning Zhang , Yabiao Wang , Mingang Chen , Chengjie Wang

Spectral bias implies an imbalance in training dynamics, whereby high-frequency components may converge substantially more slowly than low-frequency ones. To alleviate this issue, we propose a cross-attention-based architecture that…

Numerical Analysis · Mathematics 2025-12-23 Xiaodong Feng , Tao Tang , Xiaoliang Wan , Tao Zhou

Existing multi-scale solutions lead to a risk of just increasing the receptive field sizes while neglecting small receptive fields. Thus, it is a challenging problem to effectively construct adaptive neural networks for recognizing various…

Computer Vision and Pattern Recognition · Computer Science 2022-09-22 Qingbei Guo , Xiao-Jun Wu , Zhiquan Feng , Tianyang Xu , Cong Hu

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

The attention mechanism is a core component of the Transformer architecture. Various methods have been developed to compute attention scores, including multi-head attention (MHA), multi-query attention, group-query attention and so on. We…

Central to the success of Transformers is the attention block, which effectively models global dependencies among input tokens associated to a dataset. However, we theoretically demonstrate that standard attention mechanisms in transformers…

Machine Learning · Computer Science 2026-03-31 Hemanth Saratchandran

Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy. Most prior DA approaches leverage complicated and powerful deep neural…

Computer Vision and Pattern Recognition · Computer Science 2021-03-31 Shuang Li , Jinming Zhang , Wenxuan Ma , Chi Harold Liu , Wei Li

The emerging graph Transformers have achieved impressive performance for graph representation learning over graph neural networks (GNNs). In this work, we regard the self-attention mechanism, the core module of graph Transformers, as a…

Machine Learning · Computer Science 2023-10-18 Jinsong Chen , Gaichao Li , John E. Hopcroft , Kun He

Recent work has questioned the importance of the Transformer's multi-headed attention for achieving high translation quality. We push further in this direction by developing a "hard-coded" attention variant without any learned parameters.…

Computation and Language · Computer Science 2020-05-05 Weiqiu You , Simeng Sun , Mohit Iyyer
‹ Prev 1 8 9 10 Next ›