Tiny machine learning (TinyML) is a new frontier of machine learning. By squeezing deep
learning models into billions of IoT devices and microcontrollers (MCUs), we expand the …

On-device training enables the model to adapt to new data collected from the sensors by
fine-tuning a pre-trained model. Users can benefit from customized AI models without having …

Efficient on-device learning requires a small memory footprint at training time to fit the tight
memory constraint. Existing work solves this problem by reducing the number of trainable …

Recommender systems aim to provide item recommendations for users and are usually
faced with data sparsity problems (eg, cold start) in real-world scenarios. Recently pre …

Deep neural networks (DNNs) have achieved unprecedented success in the field of artificial
intelligence (AI), including computer vision, natural language processing, and speech …

Federated Learning (FL) is an emerging approach for collaboratively training Deep Neural
Networks (DNNs) on mobile devices, without private user data leaving the devices. Previous …

In this work we address task interference in universal networks by considering that a network
is trained on multiple tasks, but performs one task at a time, an approach we refer to as" …

While parameter efficient tuning (PET) methods have shown great potential with transformer
architecture on Natural Language Processing (NLP) tasks their effectiveness with large …

Inductive transfer learning has had a big impact on computer vision and NLP domains but
has not been used in the area of recommender systems. Even though there has been a …

In instance-level detection tasks (eg, object detection), reducing input resolution is an easy
option to improve runtime efficiency. However, this option severely hurts the detection …