On-Device Machine Learning: An Algorithms and Learning Theory Perspective

Dhar, Sauptik; Guo, Junyao; Liu, Jiayi; Tripathi, Samarth; Kurup, Unmesh; Shah, Mohak

doi:10.48550/arxiv.1911.00623

Cited by 16 publications

(30 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Information storage is not typically an issue with cloud systems, but every query involves delays, both in the cloud and on-device. [15,57,74]. To reduce the delay, we analyzed several lossless text compression algorithms including, Run-length encoding, Shannon-Fano encoding, Arithmetic encoding, Huffman encoding, and LZW compression [61].…”

Section: Huffman Encoding and Decodingmentioning

confidence: 99%

ODSearch: A Fast and Resource Efficient On-device Information Retrieval for Mobile and Wearable Devices

Rong¹,

Rawassizadeh²

2022

Preprint

View full text Add to dashboard Cite

Mobile and wearable technologies have promised significant changes to the healthcare industry. Although cutting-edge communication and cloud-based technologies have allowed for these upgrades, their implementation and popularization in low-income countries have been challenging. We propose ODSearch, an On-device Search framework equipped with a natural language interface for mobile and wearable devices. To implement search, ODSearch employs compression and Bloom filter, it provides near real-time search query responses without network dependency. Our experiments were conducted on a mobile phone and smartwatch. We compared ODSearch with current state-of-the-art search mechanisms, and it outperformed them on average by 55 times in execution time 1 , 26 times in energy usage, and 2.3% in memory utilization.

show abstract

Section: Huffman Encoding and Decodingmentioning

confidence: 99%

ODSearch: A Fast and Resource Efficient On-device Information Retrieval for Mobile and Wearable Devices

Rong¹,

Rawassizadeh²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Another possible challenge is the feasibility of running AI functions on IoT sensors. Due to the constraints of hardware, memory, and power resources, certain IoT sensors cannot join to train a full-size AI model [202]. In fact, advanced ML algorithms often takes a large amount of memory and power for model training and the storage of model parameters and training variables.…”

Section: Feasibility Of Deploying Ai Learning Functions On Iot Sensorsmentioning

confidence: 99%

“…• Due to constraints on hardware, memory, and power resources, certain IoT sensors cannot join to train a fullsize AI model [202]. • The high communication cost and energy consumption caused by AI training places limits on on-device FL implementation [204].…”

Section: Deploying Ai Functions On Iot Sensorsmentioning

confidence: 99%

Federated Learning for Internet of Things: A Comprehensive Survey

Nguyen,

Ding,

Pathirana

et al. 2021

Preprint

View full text Add to dashboard Cite

The Internet of Things (IoT) is penetrating many facets of our daily life with the proliferation of intelligent services and applications empowered by artificial intelligence (AI). Traditionally, AI techniques require centralized data collection and processing that may not be feasible in realistic application scenarios due to the high scalability of modern IoT networks and growing data privacy concerns. Federated Learning (FL) has emerged as a distributed collaborative AI approach that can enable many intelligent IoT applications, by allowing for AI training at distributed IoT devices without the need for data sharing. In this article, we provide a comprehensive survey of the emerging applications of FL in IoT networks, beginning from an introduction to the recent advances in FL and IoT to a discussion of their integration. Particularly, we explore and analyze the potential of FL for enabling a wide range of IoT services, including IoT data sharing, data offloading and caching, attack detection, localization, mobile crowdsensing, and IoT privacy and security. We then provide an extensive survey of the use of FL in various key IoT applications such as smart healthcare, smart transportation, Unmanned Aerial Vehicles (UAVs), smart cities, and smart industry. The important lessons learned from this review of the FL-IoT services and applications are also highlighted. We complete this survey by highlighting the current challenges and possible directions for future research in this booming area.

show abstract

“…With the rapid expansion of IoT devices in our digital universe and the explosion in the quantity of data generated by these device sensors, on-device learning has emerged as a new paradigm that enables the training of statistical models locally on the devices [1], [2]. Keeping data on device, federated learning (FL) offers an approach to do training locally in a way that a global model is collaboratively trained under the coordination of a central server [3]- [6].…”

Section: Introductionmentioning

confidence: 99%

Asynchronous Federated Learning for Sensor Data with Concept Drift

Chen¹,

Chai²,

Cheng³

et al. 2021

Preprint

View full text Add to dashboard Cite

Federated learning (FL) involves multiple distributed devices jointly training a shared model without any of the participants having to reveal their local data to a centralized server. Most of previous FL approaches assume that data on devices are fixed and stationary during the training process. However, this assumption is unrealistic because these devices usually have varying sampling rates and different system configurations. In addition, the underlying distribution of the device data can change dynamically over time, which is known as concept drift. Concept drift makes the learning process complicated because of the inconsistency between existing and upcoming data. Traditional concept drift handling techniques such as chunk based and ensemble learning-based methods are not suitable in the federated learning frameworks due to the heterogeneity of local devices. We propose a novel approach, FedConD, to detect and deal with the concept drift on local devices and minimize the effect on the performance of models in asynchronous FL. The drift detection strategy is based on an adaptive mechanism which uses the historical performance of the local models. The drift adaptation is realized by adjusting the regularization parameter of objective function on each local device. Additionally, we design a communication strategy on the server side to select local updates in a prudent fashion and speed up model convergence. Experimental evaluations on three evolving data streams and two image datasets show that FedConD detects and handles concept drift, and also reduces the overall communication cost compared to other baseline methods.

show abstract

On-Device Machine Learning: An Algorithms and Learning Theory Perspective

Cited by 16 publications

References 56 publications

ODSearch: A Fast and Resource Efficient On-device Information Retrieval for Mobile and Wearable Devices

ODSearch: A Fast and Resource Efficient On-device Information Retrieval for Mobile and Wearable Devices

Federated Learning for Internet of Things: A Comprehensive Survey

Asynchronous Federated Learning for Sensor Data with Concept Drift

Contact Info

Product

Resources

About