paper-with-me

홈 › Papers

How Particle-System Random Batch Methods Enhance Graph Transformer: Memory Efficiency and Parallel Computing Strategy

2025-11-08 · Hanwen Liu, Yixuan Ma, Shi Jin, Yuguang Wang arxiv

Attention mechanism is a significant part of Transformer models. It helps extract features from embedded vectors by adding global information and its expressivity has been proved to be powerful. Nevertheless, the quadratic complexity restricts its practicability. Although several researches have provided attention mechanism in sparse form, they are lack of theoretical analysis about the expressivity of their mechanism while reducing complexity. In this paper, we put forward Random Batch Attention (RBA), a linear self-attention mechanism, which has theoretical support of the ability to maintain its expressivity. Random Batch Attention has several significant strengths as follows: (1) Random Batch Attention has linear time complexity. Other than this, it can be implemented in parallel on a new dimension, which contributes to much memory saving. (2) Random Batch Attention mechanism can improve most of the existing models by replacing their attention mechanisms, even many previously improved attention mechanisms. (3) Random Batch Attention mechanism has theoretical explanation in convergence, as it comes from Random Batch Methods on computation mathematics. Experiments on large graphs have proved advantages mentioned above. Also, the theoretical modeling of self-attention mechanism is a new tool for future research on attention-mechanism analysis.

📄 PDF Abstract BibTeX arXiv:2511.06044

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A stochastic version of Stein Variational Gradient Descent for efficient sampling

2019-02-09 · Lei Li, Yingzhou Li, Jian-Guo Liu, Zibu Liu 외

We propose in this work RBM-SVGD, a stochastic version of Stein Variational Gradient Descent (SVGD) method for efficiently sampling from a given probability measure and thus useful for Bayesian inference. The method is t…

Bayesian Inference

Convergence, design and training of continuous-time dropout as a random batch method

2025-10-15 · Antonio Álvarez-López, Martín Hernández arxiv

We study dropout regularization in continuous-time models through the lens of random-batch methods -- a family of stochastic sampling schemes originally devised to reduce the computational cost of interacting particle sy…

Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation

2023-05-27 · NeurIPS 2023 11

Stein Variational Gradient Descent (SVGD) is a popular variational inference algorithm which simulates an interacting particle system to approximately sample from a target distribution, with impressive empirical performa…

Variational Inference

On Batching Variable Size Inputs for Training End-to-End Speech Enhancement Systems

2023-01-25 · Philippe Gonzalez, Tommy Sonne Alstrøm, Tobias May

The performance of neural network-based speech enhancement systems is primarily influenced by the model architecture, whereas training times and computational resource utilization are primarily affected by training param…

GPUSpeech Enhancement

Optimizing Hyperparameters for Quantum Data Re-Uploaders in Calorimetric Particle Identification

2024-12-16 · Léa Cassé, Bernhard Pfahringer, Albert Bifet, Frédéric Magniette

We present an application of a single-qubit Data Re-Uploading (QRU) quantum model for particle classification in calorimetric experiments. Optimized for Noisy Intermediate-Scale Quantum (NISQ) devices, this model require…

global-optimizationQuantum Machine Learning