An official website of the United States government
Monitoring a large population of dynamic processes with limited resources presents a significant challenge across various industrial sectors. This is due to 1) the inherent disparity between the available monitoring resources and the extensive number of processes to be monitored and 2) the unpredictable and heterogeneous dynamics inherent in the progression of these processes. Online learning approaches, commonly referred to as bandit methods, have demonstrated notable potential in addressing this issue by dynamically allocating resources and effectively balancing the exploitation of high-reward processes and the exploration of uncertain ones. However, most online learning algorithms are designed for 1) a centralized setting that requires data sharing across processes for accurate predictions or 2) a homogeneity assumption that estimates a single global model from decentralized data. To overcome these limitations and enable online learning in a heterogeneous population under a decentralized setting, we propose a federated collaborative online monitoring method. Our approach utilizes representation learning to capture the latent representative models within the population and introduces a novel federated collaborative UCB algorithm to estimate these models from sequentially observed decentralized data. This strategy facilitates informed monitoring of resource allocation. The efficacy of our method is demonstrated through theoretical analysis, simulation studies, and its application to decentralized cognitive degradation monitoring in Alzheimer’s disease.
more »
« less
Parallel Best Arm Identification in Heterogeneous Environments
In this paper, we study the tradeoffs between the time and the number of communication rounds of the best arm identification problem in the heterogeneous collaborative learning model, where multiple agents interact with possibly different environments and they want to learn in parallel an objective function in the aggregated environment. By proving almost tight upper and lower bounds, we show that collaborative learning in the heterogeneous setting is inherently more difficult than that in the homogeneous setting in terms of the time-round tradeoff.
more »
« less
- Award ID(s):
- 1844234
- PAR ID:
- 10574909
- Publisher / Repository:
- ACM Symposium on Parallelism in Algorithms and Architectures (SPAA) 2024
- Date Published:
- Subject(s) / Keyword(s):
- parallel learning communication complexity best arm identification heterogeneous environments
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
SITE (Ed.)Peer learning through pair programming is a type of collaborative learning that involves students working in pairs to discuss computer programming concepts or develop codes to solve problems. The Zoom breakout room method is applied to teach pair programming in a virtual classroom during the COVID-19 environment. By facilitating pair programming in a virtual learning environment, we gained valuable experience in promoting collaborative learning, active learning, and problem-based learning activities in a cloud setting.more » « less
-
This study explores the relation between students’ discourse dynamics and performance during collaborative problem-solving activities utilizing Linguistic Inquiry Word Count (LIWC). We analyzed linguistic variables from students’ communications to explore social and cognitive behavior. Participants include 279 undergraduate students from two U.S. universities engaged in a controlled lab setting using the physics related educational game named Physics Playground. Findings highlight the relationship between social and cognitive linguistic variables and student’s physics performance outcome in a virtual collaborative learning context. This study contributes to a deeper understanding of how these discourse dynamics are related to learning outcomes in collaborative learning. It provides insights for optimizing educational strategies in collaborative remote learning environments. We further discuss the potential for conducting computational linguistic modeling on learner discourse and the role of natural language processing in deriving insights on learning behavior to support collaborative learning.more » « less
-
Collaborative learning has been shown to be beneficial for children's learning performance, increasing the curiosity and intensity of the ability of cooperation. Mixed-Reality with collaborative learning is the trending research topic in the Human-Computer Interaction (HCI) area. Additionally, with the rise of attention to global warming which brings in more extreme weather and climate conditions, the earth science education would be one of the crucial topics for the next generation. Moreover, there are few augmented reality and mixed reality applications on earth science subject. In this paper, we propose a Mixed Reality Tornado Simulator which offers an earth science education in a collaborative setting. Students and the instructor can cooperate on learning the knowledge of the formation and its damage cause on human-built structures, farming, and vegetation by using our mixed reality application with the Microsoft HoloLens. Also, for evaluating the learning performance in this mixed reality setting, we propose to study the cognitive load while the student is learning the abstract knowledge in Earth Science. We will separate the student into a control group and experimental groups and use different teaching instruments to test the difference of cognitive load.more » « less
-
The wide deployment of 4G/5G has enabled connected vehicles as a perfect edge computing platform for a plethora of new services which are impossible before, such as remote real-time diagnostics and advanced driver assistance. In this work, we propose CLONE, a collaborative learning setting on the edges based on the real-world dataset collected from a large electric vehicle (EV) company. Our approach is built on top of the federated learning algorithm and long shortterm memory networks, and it demonstrates the effectiveness of driver personalization, privacy serving, latency reduction (asynchronous execution), and security protection.We choose the failure of EV battery and associated accessories as our case study to show how the CLONE solution can accurately predict failures to ensure sustainable and reliable driving in a collaborative fashion.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
