Related papers: Model Splitting Enhanced Communication-Efficient F…

Modern mobile devices have access to a wealth of data suitable for learning models, which in turn can greatly improve the user experience on the device. For example, language models can improve speech recognition and text entry, and image…

In frequency division duplex mode, the downlink channel state information (CSI) should be sent to the base station through feedback links so that the potential gains of a massive multiple-input multiple-output can be exhibited. However,…

Federated learning (FL) enables the training of a model leveraging decentralized data in client sites while preserving privacy by not collecting data. However, one of the significant challenges of FL is limited computation and low…

Massive MIMO systems rely on accurate Channel State Information (CSI) feedback to enable high-gain beam-forming. However, the feedback overhead scales linearly with the number of antennas, presenting a major bottleneck. While recent deep…

There are situations where data relevant to machine learning problems are distributed across multiple locations that cannot share the data due to regulatory, competitiveness, or privacy reasons. Machine learning approaches that require data…

Multicell joint processing can mitigate inter-cell interference and thereby increase the spectral efficiency of cellular systems. Most previous work has assumed phase-aligned (coherent) transmissions from different base transceiver stations…

The rapid advancement of large AI models imposes stringent demands on data volume and computational resources. Federated learning, though designed to exploit distributed data and computational resources, faces data shortage from limited…

A Federated Learning (FL) system collaboratively trains neural networks across devices and a server but is limited by significant on-device computation costs. Split Federated Learning (SFL) systems mitigate this by offloading a block of…

Federated Learning (FL) enables participant devices to collaboratively train deep learning models without sharing their data with the server or other devices, effectively addressing data privacy and computational concerns. However, FL faces…

Automatic Speech Recognition models require large amount of speech data for training, and the collection of such data often leads to privacy concerns. Federated learning has been widely used and is considered to be an effective…

Federated learning is a distributed machine learning approach to privacy preservation and two major technical challenges prevent a wider application of federated learning. One is that federated learning raises high demands on communication,…

This paper studies a federated edge learning system, in which an edge server coordinates a set of edge devices to train a shared machine learning model based on their locally distributed data samples. During the distributed training, we…

Modern IEEE 802.11 (Wi-Fi) networks extensively rely on multiple-input multiple-output (MIMO) to significantly improve throughput. To correctly beamform MIMO transmissions, the access point needs to frequently acquire a beamforming matrix…

To get channel state information (CSI) at a base station (BS), most of researches on massive multiple-input multiple-output (MIMO) systems consider time division duplexing (TDD) to get benefit from the uplink and downlink channel…

Federated learning (FL) is able to manage edge devices to cooperatively train a model while maintaining the training data local and private. One common assumption in FL is that all edge devices share the same machine learning model in…

Distributed learning techniques such as federated learning have enabled multiple workers to train machine learning models together to reduce the overall training time. However, current distributed training algorithms (centralized or…

Transformers have shown improved performance when compared to previous architectures for sequence processing such as RNNs. Despite their sizeable performance gains, as recently suggested, the model is computationally expensive to train and…

Accurate and low-overhead channel state information (CSI) feedback is essential to boost the capacity of frequency division duplex (FDD) massive multiple-input multiple-output (MIMO) systems. Deep learning-based CSI feedback significantly…

We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…

In Wi-Fi systems, channel state information (CSI) plays a crucial role in enabling access points to execute beamforming operations. However, the feedback overhead associated with CSI significantly hampers the throughput improvements. Recent…