Related papers: It's always personal: Using Early Exits for Effici…

Large pre-trained models have exhibited remarkable achievements across various domains. The substantial training costs associated with these models have led to wide studies of fine-tuning for effectively harnessing their capabilities in…

The deployment of inference services at the network edge, called edge inference, offloads computation-intensive inference tasks from mobile devices to edge servers, thereby enhancing the former's capabilities and battery lives. In a…

Mixture-of-Experts (MoE) model architectures can significantly reduce the number of activated parameters per token, enabling computationally efficient training and inference. However, their large overall parameter counts and model sizes…

The rapid rise of IoT and Big Data has facilitated copious data driven applications to enhance our quality of life. However, the omnipresent and all-encompassing nature of the data collection can generate privacy concerns. Hence, there is a…

On-device learning remains a formidable challenge, especially when dealing with resource-constrained devices that have limited computational capabilities. This challenge is primarily rooted in two key issues: first, the memory available on…

Mixture-of-Experts (MoE) has become the de facto architecture for hundred-billion-parameter language models, yet its advantages at sub-billion scales for on-device deployment remain largely unexplored. To close this gap, we present…

Computational offloading is a promising approach for overcoming resource constraints on client devices by moving some or all of an application's computations to remote servers. With the advent of specialized hardware accelerators, client…

Transfer learning, a technique commonly used in generative artificial intelligence, allows neural network models to bring prior knowledge to bear when learning a new task. This study demonstrates that transfer learning significantly…

Training deep learning models on mobile devices recently becomes possible, because of increasing computation power on mobile hardware and the advantages of enabling high user experiences. Most of the existing work on machine learning at…

To address the challenge of increasing network size, researchers have developed sparse models through network pruning. However, maintaining model accuracy while achieving significant speedups on general computing devices remains an open…

Early Exit (EE) techniques have emerged as a means to reduce inference latency in Deep Neural Networks (DNNs). The latency improvement and accuracy in these techniques crucially depend on the criteria used to make exit decisions. We propose…

Continual learning (CL) trains NN models incrementally from a continuous stream of tasks. To remember previously learned knowledge, prior studies store old samples over a memory hierarchy and replay them when new tasks arrive. Edge devices…

Mobile authentication using behavioral biometrics has been an active area of research. Existing research relies on building machine learning classifiers to recognize an individual's unique patterns. However, these classifiers are not…

Originated from distributed learning, federated learning enables privacy-preserved collaboration on a new abstracted level by sharing the model parameters only. While the current research mainly focuses on optimizing learning algorithms and…

Deep neural networks have become larger over the years with increasing demand of computational resources for inference; incurring exacerbate costs and leaving little room for deployment on devices with limited battery and other resources…

Most federated learning (FL) approaches assume a fixed device set. However, real-world scenarios often involve devices dynamically joining or leaving the system, driven by, e.g., user mobility patterns or handovers across cell boundaries.…

With the increased usage of AI accelerators on mobile and edge devices, on-device machine learning (ML) is gaining popularity. Thousands of proprietary ML models are being deployed today on billions of untrusted devices. This raises serious…

Deploying deep neural networks on mobile devices is a challenging task. Current model compression methods such as matrix decomposition effectively reduce the deployed model size, but still cannot satisfy real-time processing requirement.…

Although deep learning has made strides in the field of deep noise suppression, leveraging deep architectures on resource-constrained devices still proved challenging. Therefore, we present an early-exiting model based on nsNet2 that…

On-device learning enables edge devices to continually adapt the AI models to new data, which requires a small memory footprint to fit the tight memory constraint of edge devices. Existing work solves this problem by reducing the number of…