The ever-growing artificial intelligence (AI) applications have greatly reshaped our world in
many areas, eg, smart home, computer vision, natural language processing, etc. Behind …

Nowadays, the training data and neural network models are getting increasingly large. The
training time of deep learning will become unbearably long on a single machine. To reduce …

The proliferation of Internet-of-Things (IoT) devices and cloud-computing applications over
siloed data centers is motivating renewed interest in the collaborative training of a shared …

Decentralized training of deep learning models is a key element for enabling data privacy
and on-device learning over networks. In realistic learning scenarios, the presence of …

Fine-tuning large-scale pre-trained vision models to downstream tasks is a standard
technique for achieving state-of-the-art performance on computer vision benchmarks …

Decentralized learning enables a group of collaborative agents to learn models using a
distributed dataset without the need for a central parameter server. Recently, decentralized …

Recent success of deep neural networks (DNNs) hinges on the availability of large-scale
dataset; however, training on such dataset often poses privacy risks for sensitive training …

The rank of neural networks measures information flowing across layers. It is an instance of
a key structural condition that applies across broad domains of machine learning. In …

Abstract In Federated Learning (FL), a common approach for aggregating local solutions
across clients is periodic full model averaging. It is, however, known that different layers of …

Decentralized image classification plays a key role in various scenarios due to its attractive
properties, including tolerating high network latency and less prone to single-point failures …