English
Related papers

Related papers: Supplementary Material: Implementation and Experim…

200 papers

Multimodal learning faces a fundamental tension between deep, fine-grained fusion and computational scalability. While cross-attention models achieve strong performance through exhaustive pairwise fusion, their quadratic complexity is…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Yusuf Shihata

Graph neural networks (GNNs) have recently exploded in popularity thanks to their broad applicability to graph-related problems such as quantum chemistry, drug discovery, and high energy physics. However, meeting demand for novel GNN models…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-10-20 Rishov Sarkar , Stefan Abi-Karam , Yuqi He , Lakshmi Sathidevi , Cong Hao

Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods used a subset of combinations of component functions and weight matrices within the random feature paradigm. We…

Machine Learning · Computer Science 2025-09-24 Duke Nguyen , Du Yin , Aditya Joshi , Flora Salim

Attention accounts for an increasingly dominant fraction of total computation during inference for mixture-of-experts (MoE) models, making efficient acceleration critical. Emerging domain-specific accelerators for large model inference are…

Hardware Architecture · Computer Science 2026-04-03 Chi Zhang , Luca Colagrande , Renzo Andri , Luca Benini

Modern autoregressive models rely on attention, yet the Softmax full attention in Transformers scales quadratically with sequence length. Sliding Window Attention (SWA) achieves linear-time encoding/decoding by constraining the attention…

Machine Learning · Computer Science 2026-01-08 Jiaxu Liu , Yuhe Bai , Xiangyu Yin , Christos-Savvas Bouganis

In this paper, we propose a novel method for enhancing security in privacy-preserving federated learning using the Vision Transformer. In federated learning, learning is performed by collecting updated information without collecting raw…

Cryptography and Security · Computer Science 2024-10-01 Hiroto Sawada , Shoko Imaizumi , Hitoshi Kiya

We explore Multi-Head FFN (MH-FFN) as a replacement of FFN in the Transformer architecture, motivated by the structural similarity between single-head attention and FFN. While multi-head mechanisms enhance expressivity in attention, naively…

Machine Learning · Computer Science 2025-12-09 Minshen Zhang , Xiang Hu , Jianguo Li , Wei Wu , Kewei Tu

Speech separation always faces the challenge of handling prolonged time sequences. Past methods try to reduce sequence lengths and use the Transformer to capture global information. However, due to the quadratic time complexity of the…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-28 Haoxu Wang , Yiheng Jiang , Gang Qiao , Pengteng Shi , Biao Tian

We propose the joint graph attention neural network (GAT), clustering with adaptive neighbors (CAN) and probabilistic graphical model for dynamic power flow analysis and fault characteristics. In fact, computational efficiency is the main…

Machine Learning · Computer Science 2025-03-25 Tan Le , Van Le

The attention layer, a core component of Transformer-based LLMs, brings out inefficiencies in current GPU systems due to its low operational intensity and the substantial memory requirements of KV caches. We propose a High-bandwidth…

Hardware Architecture · Computer Science 2025-12-19 Myunghyun Rhee , Joonseop Sim , Taeyoung Ahn , Seungyong Lee , Daegun Yoon , Euiseok Kim , Kyoung Park , Youngpyo Joo , Hoshik Kim

We introduce $\textbf{F}$uture $\textbf{LA}$tent $\textbf{RE}$presentation Alignment ($\textbf{FLARE}$), a novel framework that integrates predictive latent world modeling into robot policy learning. By aligning features from a diffusion…

Federated Learning (FL) since proposed has been applied in many fields, such as credit assessment, medical, etc. Because of the difference in the network or computing resource, the clients may not update their gradients at the same time…

Machine Learning · Computer Science 2021-11-19 Zhicheng Zhou , Hailong Chen , Kunhua Li , Fei Hu , Bingjie Yan , Jieren Cheng , Xuyan Wei , Bernie Liu , Xiulai Li , Fuwen Chen , Yongji Sui

Graph-based and sequential methods are two popular recommendation paradigms, each excelling in its domain but lacking the ability to leverage signals from the other. To address this, we propose a novel method that integrates both approaches…

Information Retrieval · Computer Science 2025-01-30 Yuwei Cao , Liangwei Yang , Zhiwei Liu , Yuqing Liu , Chen Wang , Yueqing Liang , Hao Peng , Philip S. Yu

Although the capacity of deep generative models for image generation, such as Diffusion Models (DMs) and Generative Adversarial Networks (GANs), has dramatically improved in recent years, much of their success can be attributed to…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Emilio Morales-Juarez , Gibran Fuentes-Pineda

The Transformer architecture has recently gained considerable attention in the field of graph representation learning, as it naturally overcomes several limitations of Graph Neural Networks (GNNs) with customized attention mechanisms or…

Machine Learning · Computer Science 2025-04-01 Jianqing Liang , Min Chen , Jiye Liang

Transformers and large language models (LLMs), powered by the attention mechanism, have transformed numerous AI applications, driving the need for specialized hardware accelerators. A major challenge in these accelerators is efficiently…

Machine Learning · Computer Science 2025-07-23 Vasileios Titopoulos , Kosmas Alexandridis , Giorgos Dimitrakopoulos

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

The quadratic computation complexity of self-attention has been a persistent challenge when applying Transformer models to vision tasks. Linear attention, on the other hand, offers a much more efficient alternative with its linear…

Computer Vision and Pattern Recognition · Computer Science 2023-09-04 Dongchen Han , Xuran Pan , Yizeng Han , Shiji Song , Gao Huang

Attention-based models, exemplified by the Transformer, can effectively model long range dependency, but suffer from the quadratic complexity of self-attention operation, making them difficult to be adopted for high-resolution image…

Computer Vision and Pattern Recognition · Computer Science 2021-12-28 Long Zhao , Zizhao Zhang , Ting Chen , Dimitris N. Metaxas , Han Zhang

Transformers have proved to be very effective for visual recognition tasks. In particular, vision transformers construct compressed global representations through self-attention and learnable class tokens. Multi-resolution transformers have…

Computer Vision and Pattern Recognition · Computer Science 2022-12-16 Loic Themyr , Clement Rambour , Nicolas Thome , Toby Collins , Alexandre Hostettler