About
Working on Video Infrastracutre, specially on optimization of live streaming infra behind…
Activity
-
A couple of weeks ago I gave a talk at HPE on Chapel's GPU programming support. Public version of my slides are now available on the Chapel website…
A couple of weeks ago I gave a talk at HPE on Chapel's GPU programming support. Public version of my slides are now available on the Chapel website…
Liked by Yongbo Li
-
If you are attending NeurIPS 2023 in New Orleans this week, please check out our work: 1. "Every Parameter Matters: Ensuring the Convergence of…
If you are attending NeurIPS 2023 in New Orleans this week, please check out our work: 1. "Every Parameter Matters: Ensuring the Convergence of…
Liked by Yongbo Li
-
Excited to present our research paper on Federated Learning at NeurIPS 2023! This is one of my favorite papers so far that offers an in-depth…
Excited to present our research paper on Federated Learning at NeurIPS 2023! This is one of my favorite papers so far that offers an in-depth…
Liked by Yongbo Li
Experience
Education
-
The George Washington University
-
My primary research interests were system security, energy-aware mobile computing, and edge computing optimization
Publications
-
Mobile Ad Prefetching and Energy Optimization via Tail Energy Accounting
IEEE Transactions on Mobile Computing
Accurately determining the network energy consumption of each software principal when multiple ones are active is the key to mobile energy optimization. Tail energy accounting, which attributes tail energy to individual software principals, remains an open problem. Besides, tail energy has also become a major energy drain, especially in mobile ad modules that generate frequent, intermittent network traffics by on-demand ad downloading. In this paper, we propose a systematic framework for mobile…
Accurately determining the network energy consumption of each software principal when multiple ones are active is the key to mobile energy optimization. Tail energy accounting, which attributes tail energy to individual software principals, remains an open problem. Besides, tail energy has also become a major energy drain, especially in mobile ad modules that generate frequent, intermittent network traffics by on-demand ad downloading. In this paper, we propose a systematic framework for mobile ad prefetching and energy optimization, based on a novel tail energy accounting policy using cooperative game theory. In particular, we maximize the sum of deadline- and energy-aware ad utility, by jointly determining apps' aggressiveness in ad prefetching. The proposed tail energy accounting not only characterizes the energy profile of each app's ad module, a crucial input in energy optimization, but also enables an efficient solution by decoupling decision making of individual apps. The proposed framework is implemented on Android with negligible performance/network overhead. Using real-world apps and usage traces, we demonstrate a significant reduction in mobile network energy consumption by up to 45% compared with existing approaches. To the best of our knowledge, it is the first fully implemented ad management system transparent to apps and ad ecosystem.
Other authorsSee publication -
Multichoice games for optimizing task assignment in edge computing
IEEE/Globecom
Mobile Edge Computing has fastly become a promising diagram to meet the ever-increasing demands imposed by emerging domains of applications and reduce the reliance on remote data centers in traditional cloud computing. In this paper, we address two problems unique in heterogeneous edge computing: the cost accounting and task assignment. To determine the cost of each unit of task being concurrently processed on an edge device, we propose to model the problem as a multichoice game, and use…
Mobile Edge Computing has fastly become a promising diagram to meet the ever-increasing demands imposed by emerging domains of applications and reduce the reliance on remote data centers in traditional cloud computing. In this paper, we address two problems unique in heterogeneous edge computing: the cost accounting and task assignment. To determine the cost of each unit of task being concurrently processed on an edge device, we propose to model the problem as a multichoice game, and use Shapley Value for cost accounting. With the total cost decoupled, we are able to leverage the distributive Hungarian algorithm to solve the task assignment problem efficiently. We adopt a hybrid manner for evaluations: we profile the costs (including energy and data transmission costs) using a fully implemented workload offloading framework in an edge environment, then the cost profiles are used to drive the simulations. Results show that our policy of task assignment guided by multichoice Shapley value is able to consistently outperform the two other baselines: Random policy and the policy of Hungarian assignment algorithm based on Even energy accounting. The advantage of our policy is further enlarged when the heterogeneity level of the network or computing resource in edge environments is increased. We also show interesting patterns of the joint effects of different resources’ heterogeneity levels and the weighting factor between them, which provide useful inputs for edge resource optimization and management.
Other authors -
Capitalizing on the Promise of Ad Prefetching in Real-World Mobile Systems
The 14th IEEE International Conference on Mobile Ad-hoc and Sensor Systems (MASS)
-
SARRE: Semantics-Aware Rule Recommendation and Enforcement for Event Paths on Android
IEEE Transaction on Information Forensics and Security
This paper presents a semantics-aware rule recommendation and enforcement (SARRE) system for taming information leakage on Android. SARRE leverages statistical analysis and a novel application of minimum path cover algorithm to identify system event paths from dynamic runtime monitoring. Then, an online recommendation system is developed to automatically assign a fine-grained security rule to each event path, capitalizing on both known security rules and application semantic information. The…
This paper presents a semantics-aware rule recommendation and enforcement (SARRE) system for taming information leakage on Android. SARRE leverages statistical analysis and a novel application of minimum path cover algorithm to identify system event paths from dynamic runtime monitoring. Then, an online recommendation system is developed to automatically assign a fine-grained security rule to each event path, capitalizing on both known security rules and application semantic information. The proposed SARRE system is prototyped on Android devices and evaluated using real-world malware samples and popular apps from Google Play spanning multiple categories. Our results show that SARRE achieves 93.8% precision and 96.4% recall in identifying the event paths, compared with tainting technique. Also, the average difference between rule recommendation and manual configuration is less than 5%, validating the effectiveness of the automatic rule recommendation. It is also demonstrated that by enforcing the recommended security rules through a camouflage engine, SARRE can effectively prevent information leakage and enable fine-grained protection over private data with a very small performance overhead.
Other authorsSee publication
Patents
-
CIAdroid: Causality-based Information Flow and Activity Path Identification on Android
Filed US 015-048-lan
Provisional Filing
-
A Handheld Power Efficient SmartWiFi-enabled Device
Issued CN CN201220276679.3
More activity by Yongbo
-
Gave an invited seminar talk at IE@Purdue. Thank Vaneet Aggarwal and Ana María Estrada Gómez for the invitation! The new “Gateway” building and labs…
Gave an invited seminar talk at IE@Purdue. Thank Vaneet Aggarwal and Ana María Estrada Gómez for the invitation! The new “Gateway” building and labs…
Liked by Yongbo Li
-
Happy to present our work ‘Distributional-Utility Actor-Critic for Network Performance Guarantee’ at the Mobihoc 2023.
Happy to present our work ‘Distributional-Utility Actor-Critic for Network Performance Guarantee’ at the Mobihoc 2023.
Liked by Yongbo Li
-
It was great to co-chair and host the ACM MobiHoc 2023 conference last week right here at GW! Thanks to the entire organizing committee including my…
It was great to co-chair and host the ACM MobiHoc 2023 conference last week right here at GW! Thanks to the entire organizing committee including my…
Liked by Yongbo Li
-
Freed is building an AI clinician assistant to transform the healthcare system for the modern era. I ended my 10-year Meta career to create this…
Freed is building an AI clinician assistant to transform the healthcare system for the modern era. I ended my 10-year Meta career to create this…
Liked by Yongbo Li
-
Great KPMG Lakehouse event discussing health equity and AI. If we don’t work together on it now, the existing gap may be getting even wider.
Great KPMG Lakehouse event discussing health equity and AI. If we don’t work together on it now, the existing gap may be getting even wider.
Liked by Yongbo Li
-
I’m happy to share that I’m starting a new position as Senior Software Engineer - cloud infrastructure at Bloomberg! #WorkAtBloomberg
I’m happy to share that I’m starting a new position as Senior Software Engineer - cloud infrastructure at Bloomberg! #WorkAtBloomberg
Liked by Yongbo Li
-
Excited to present our work on Reinforcement Learning at NeurIPS 2022! Huge thanks to my professors Prof.Tian Lan and Prof.Vaneet Aggarwal…
Excited to present our work on Reinforcement Learning at NeurIPS 2022! Huge thanks to my professors Prof.Tian Lan and Prof.Vaneet Aggarwal…
Liked by Yongbo Li
-
I started my first job at Meta in October 2022 but wasn't able to join any team due to hiring freeze. After spending a month in the bootcamp, I was…
I started my first job at Meta in October 2022 but wasn't able to join any team due to hiring freeze. After spending a month in the bootcamp, I was…
Liked by Yongbo Li
-
Last week I shared that I will be leaving Meta after 8 years (https://bit.ly/3BGPA1a). I am excited to share that I have joined #Figma as VP of…
Last week I shared that I will be leaving Meta after 8 years (https://bit.ly/3BGPA1a). I am excited to share that I have joined #Figma as VP of…
Liked by Yongbo Li
People also viewed
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Yongbo Li in United States
-
Yongbo Mark Li
Undergrad in Sports Management at NYU
-
yongbo li
SAS Engineer at JinYing
-
John Yongbo Li, MD, MBA
-
Yongbo Li
7 others named Yongbo Li in United States are on LinkedIn
See others named Yongbo Li