相关论文: Communication-Efficient Federated Learning for Neu…

While neural machine translation (NMT) models provide improved translation quality in an elegant, end-to-end framework, it is less clear what they learn about language. Recent work has started evaluating the quality of vector…

With the recent developments in the field of Natural Language Processing, there has been a rise in the use of different architectures for Neural Machine Translation. Transformer architectures are used to achieve state-of-the-art accuracy,…

Multimodal federated learning (MFL) aims to enrich model training in FL settings where clients are collecting measurements across multiple modalities. However, key challenges to MFL remain unaddressed, particularly in heterogeneous network…

With increasing privacy concerns on data, recent studies have made significant progress using federated learning (FL) on privacy-sensitive natural language processing (NLP) tasks. Much literature suggests fully fine-tuning pre-trained…

Multilingual neural machine translation (MNMT) trained in multiple language pairs has attracted considerable attention due to fewer model parameters and lower training costs by sharing knowledge among multiple languages. Nonetheless,…

We compare communication efficiencies of two compelling distributed machine learning approaches of split learning and federated learning. We show useful settings under which each method outperforms the other in terms of communication…

Machine Learning (ML) systems are getting increasingly popular, and drive more and more applications and services in our daily life. This has led to growing concerns over user privacy, since human interaction data typically needs to be…

Personalized federated learning (FL) aims to train model(s) that can perform well for individual clients that are highly data and system heterogeneous. Most work in personalized FL, however, assumes using the same model architecture at all…

Hybrid Language Models (HLMs) combine the low-latency efficiency of Small Language Models (SLMs) on edge devices with the high accuracy of Large Language Models (LLMs) on centralized servers. Unlike traditional end-to-end LLM inference,…

Federated learning (FL) enables a loose set of participating clients to collaboratively learn a global model via coordination by a central server and with no need for data sharing. Existing FL approaches that rely on complex algorithms with…

Transfer learning via fine-tuning pre-trained transformer models has gained significant success in delivering state-of-the-art results across various NLP tasks. In the absence of centralized data, Federated Learning (FL) can benefit from…

Federated learning (FL) has recently emerged as an important and promising learning scheme in IoT, enabling devices to jointly learn a model without sharing their raw data sets. However, as the training data in FL is not collected and…

Neural machine translation (NMT) approaches have improved the state of the art in many machine translation settings over the last couple of years, but they require large amounts of training data to produce sensible output. We demonstrate…

The field of neural machine translation (NMT) has changed with the advent of large language models (LLMs). Much of the recent emphasis in natural language processing (NLP) has been on modeling machine translation and many other problems…

Federated Learning (FL) incurs high communication overhead, which can be greatly alleviated by compression for model updates. Yet the tradeoff between compression and model accuracy in the networked environment remains unclear and, for…

Multilingual neural machine translation (NMT) enables training a single model that supports translation from multiple source languages into multiple target languages. In this paper, we push the limits of multilingual NMT in terms of number…

Federated Learning (FL) is a well-known framework for successfully performing a learning task in an edge computing scenario where the devices involved have limited resources and incomplete data representation. The basic assumption of FL is…

Federated learning (FL) enables edge-devices to collaboratively learn a model without disclosing their private data to a central aggregating server. Most existing FL algorithms require models of identical architecture to be deployed across…

Communication on heterogeneous edge networks is a fundamental bottleneck in Federated Learning (FL), restricting both model capacity and user participation. To address this issue, we introduce two novel strategies to reduce communication…

Multilingual neural machine translation (NMT), which translates multiple languages using a single model, is of great practical importance due to its advantages in simplifying the training process, reducing online maintenance costs, and…