English
Related papers

Related papers: Parallel Split Learning with Global Sampling

200 papers

We address the challenging problem of Long-Tailed Semi-Supervised Learning (LTSSL) where labeled data exhibit imbalanced class distribution and unlabeled data follow an unknown distribution. Unlike in balanced SSL, the generated…

Computer Vision and Pattern Recognition · Computer Science 2024-04-04 Chengcheng Ma , Ismail Elezi , Jiankang Deng , Weiming Dong , Changsheng Xu

The classical line search for learning rate (LR) tuning in the stochastic gradient descent (SGD) algorithm can tame the convergence slowdown due to data-sampling noise. In a federated setting, wherein the client heterogeneity introduces a…

Machine Learning · Computer Science 2025-10-28 Geetika , Somya Tyagi , Bapi Chatterjee

Most machine learning and deep neural network algorithms rely on certain iterative algorithms to optimise their utility/cost functions, e.g. Stochastic Gradient Descent. In distributed learning, the networked nodes have to work…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-10-06 Liang Wang , Ben Catterall , Richard Mortier

Federated Learning (FL), Split Learning (SL), and SplitFed Learning (SFL) are three recent developments in distributed machine learning that are gaining attention due to their ability to preserve the privacy of raw data. Thus, they are…

Machine Learning · Computer Science 2021-09-21 Praveen Joshi , Chandra Thapa , Seyit Camtepe , Mohammed Hasanuzzamana , Ted Scully , Haithem Afli

Federated learning (FL) enables collaborative model training across distributed edge devices while preserving data privacy, and typically operates in a round-based synchronous manner. However, synchronous FL suffers from latency bottlenecks…

Machine Learning · Computer Science 2026-03-17 Asaf Goren , Natalie Lang , Nir Shlezinger , Alejandro Cohen

In this paper, we propose to tackle the challenging few-shot learning (FSL) problem by learning global class representations using both base and novel class training samples. In each training episode, an episodic class mean computed from a…

Computer Vision and Pattern Recognition · Computer Science 2019-08-15 Tiange Luo , Aoxue Li , Tao Xiang , Weiran Huang , Liwei Wang

3D Gaussian Splatting (3DGS) is increasingly popular for 3D reconstruction due to its superior visual quality and rendering speed. However, 3DGS training currently occurs on a single GPU, limiting its ability to handle high-resolution and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-10 Hexu Zhao , Haoyang Weng , Daohan Lu , Ang Li , Jinyang Li , Aurojit Panda , Saining Xie

Test-time scaling (TTS) has gained widespread attention for enhancing LLM reasoning. Existing approaches such as Best-of-N and majority voting are limited as their performance depends on the quality of candidate responses, making them…

Machine Learning · Computer Science 2026-04-28 Qibin Wang , Pu Zhao , Shaohan Huang , Fangkai Yang , Lu Wang , Furu Wei , Qingwei Lin , Saravan Rajmohan , Dongmei Zhang

Federated learning (FL) and split learning (SL) are two popular distributed machine learning approaches. Both follow a model-to-data scenario; clients train and test machine learning models without sharing raw data. SL provides better model…

Machine Learning · Computer Science 2022-02-18 Chandra Thapa , M. A. P. Chamikara , Seyit Camtepe , Lichao Sun

Split learning (SL) enables collaborative training of large language models (LLMs) between resource-constrained edge devices and compute-rich servers by partitioning model computation across the network boundary. However, existing SL…

Machine Learning · Computer Science 2026-04-07 Aakriti Lnu , Zhe Li , Dandan Liang , Chao Huang , Rui Li , Haibo Yang

Parallel aggregation is a ubiquitous operation in data analytics that is expressed as GROUP BY in SQL, reduce in Hadoop, or segment in TensorFlow. Parallel aggregation starts with an optional local pre-aggregation step and then repartitions…

Databases · Computer Science 2018-11-30 Feilong Liu , Ario Salmasi , Spyros Blanas , Anastasios Sidiropoulos

Graph neural networks (GNNs) are powerful tools for learning from graph data and are widely used in various applications such as social network recommendation, fraud detection, and graph search. The graphs in these applications are…

Machine Learning · Computer Science 2021-06-14 Jialin Dong , Da Zheng , Lin F. Yang , Geroge Karypis

In this paper, we study contrastive learning from an optimization perspective, aiming to analyze and address a fundamental issue of existing contrastive learning methods that either rely on a large batch size or a large dictionary of…

Machine Learning · Computer Science 2022-09-22 Zhuoning Yuan , Yuexin Wu , Zi-Hao Qiu , Xianzhi Du , Lijun Zhang , Denny Zhou , Tianbao Yang

Continual self-supervised learning (CSSL) methods have gained increasing attention in remote sensing (RS) due to their capability to learn new tasks sequentially from continuous streams of unlabeled data. Existing CSSL methods, while…

Computer Vision and Pattern Recognition · Computer Science 2025-05-19 Lars Möllenbrok , Behnood Rasti , Begüm Demir

Cross-view geo-localization aims to match images of the same target from different platforms, e.g., drone and satellite. It is a challenging task due to the changing appearance of targets and environmental content from different views. Most…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Quan Chen , Tingyu Wang , Zihao Yang , Haoran Li , Rongfeng Lu , Yaoqi Sun , Bolun Zheng , Chenggang Yan

Federated learning (FL) enables collaborative machine learning across distributed data owners, but data heterogeneity poses a challenge for model calibration. While prior work focused on improving accuracy for non-iid data, calibration…

Machine Learning · Computer Science 2024-06-05 Hongyi Peng , Han Yu , Xiaoli Tang , Xiaoxiao Li

We propose sequenced-replacement sampling (SRS) for training deep neural networks. The basic idea is to assign a fixed sequence index to each sample in the dataset. Once a mini-batch is randomly drawn in each training iteration, we refill…

Machine Learning · Computer Science 2018-10-22 Chiu Man Ho , Dae Hoon Park , Wei Yang , Yi Chang

Techniques such as ensembling and distillation promise model quality improvements when paired with almost any base model. However, due to increased test-time cost (for ensembles) and increased complexity of the training pipeline (for…

Machine Learning · Computer Science 2020-08-24 Rohan Anil , Gabriel Pereyra , Alexandre Passos , Robert Ormandi , George E. Dahl , Geoffrey E. Hinton

The recent success of deep learning applications has coincided with those widely available powerful computational resources for training sophisticated machine learning models with huge datasets. Nonetheless, training large models such as…

Machine Learning · Computer Science 2022-01-03 Farley Lai , Asim Kadav , Erik Kruus

Modern machine learning models are typically trained using Stochastic Gradient Descent (SGD) on massively parallel computing resources such as GPUs. Increasing mini-batch size is a simple and direct way to utilize the parallel computing…

Machine Learning · Statistics 2019-03-05 Siyuan Ma , Mikhail Belkin