Related papers: A Two-Stage Data Selection Framework for Data-Effi…

In this paper, to deal with the heterogeneity in federated learning (FL) systems, a knowledge distillation (KD) driven training framework for FL is proposed, where each user can select its neural network model on demand and distill…

The digital twin edge network (DITEN) is a significant paradigm in the sixth-generation wireless system (6G) that aims to organize well-developed infrastructures to meet the requirements of evolving application scenarios. However, the…

Learning at the edge is a challenging task from several perspectives, since data must be collected by end devices (e.g. sensors), possibly pre-processed (e.g. data compression), and finally processed remotely to output the result of…

Segmentation-based, two-stage neural network has shown excellent results in the surface defect detection, enabling the network to learn from a relatively small number of samples. In this work, we introduce end-to-end training of the…

The Federated Learning (FL) workflow of training a centralized model with distributed data is growing in popularity. However, until recently, this was the realm of contributing clients with similar computing capability. The fast expanding…

With the prevalence of Large Learning Models (LLM), Split Federated Learning (SFL), which divides a learning model into server-side and client-side models, has emerged as an appealing technology to deal with the heavy computational burden…

Efficient Federated learning (FL) is crucial for training deep networks over devices with limited compute resources and bounded networks. With the advent of big data, devices either generate or collect multimodal data to train either…

Benefiting from high capacity for capturing complex temporal patterns, deep learning (DL) has significantly advanced time series forecasting (TSF). However, deep models tend to suffer from severe overfitting due to the inherent…

Federated learning (FL) enables collaboratively training a model while keeping the training data decentralized and private. However, one significant impediment to training a model using FL, especially large models, is the resource…

The vast advances in Machine Learning over the last ten years have been powered by the availability of suitably prepared data for training purposes. The future of ML-enabled enterprise hinges on data. As such, there is already a vibrant…

Federated learning refers to conducting training on multiple distributed devices and collecting model weights from them to derive a shared machine-learning model. This allows the model to get benefit from a rich source of data available…

Federated Learning (FL) enables multiple devices to collaboratively train a shared model while ensuring data privacy. The selection of participating devices in each training round critically affects both the model performance and training…

High-quality data plays a critical role in the pretraining and fine-tuning of large language models (LLMs), even determining their performance ceiling to some degree. Consequently, numerous data selection methods have been proposed to…

Federated learning (FL) is usually performed on resource-constrained edge devices, e.g., with limited memory for the computation. If the required memory to train a model exceeds this limit, the device will be excluded from the training.…

Data selection improves computational efficiency by choosing informative subsets of training samples. However, existing methods ignore the compute budget, treating data selection and importance evaluation independently of compute budget…

The emerging data-driven methods based on artificial intelligence (AI) have paved the way for intelligent, flexible, and adaptive network management in vehicular applications. To enhance network management towards network automation, this…

This paper describes our solution for the video recognition task of ActivityNet Kinetics challenge that ranked the 1st place. Most of existing state-of-the-art video recognition approaches are in favor of an end-to-end pipeline. One…

Many recent deep learning platforms rely on third-party libraries (such as cuBLAS) to utilize the computing power of modern hardware accelerators (such as GPUs). However, we observe that they may achieve suboptimal performance because the…

Distributed deep learning (DDL) training systems are designed for cloud and data-center environments that assumes homogeneous compute resources, high network bandwidth, sufficient memory and storage, as well as independent and identically…

On-device training is an emerging approach in machine learning where models are trained on edge devices, aiming to enhance privacy protection and real-time performance. However, edge devices typically possess restricted computational power…