Hongyi Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Hongyi Wang has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Zhenhua Li
Tsinghua University, Beijing, China
7 shared publications - Feng Qian
University of Southern California
3 shared publications - Jiaxing Qiu
Tsinghua University, Beijing, China
3 shared publications - Yunhao Liu
Tsinghua University
3 shared publications - Hao Lin
Tsinghua University, Beijing, China
2 shared publications - Jie Wu
Cloud Computing Research Institute, China Telecom
2 shared publications
Latest Publications
- Open Access
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 780-795
CFMoE: Cache-Friendly Mixture of Experts Model Serving System on Edge Devices
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 780-795
Open AccessCFMoE: Cache-Friendly Mixture of Experts Model Serving System on Edge Devices
- Open Access
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 391-406
Cellulars Go Underground: Practical Obstacles and Effective Mitigation
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 391-406
Open AccessCellulars Go Underground: Practical Obstacles and Effective Mitigation
- Open Access
- 28 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 550-564
LMTracer: Fine-Grained and Real-Time Performance Profiling for Production LLM Systems
- 28 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 550-564
Open AccessLMTracer: Fine-Grained and Real-Time Performance Profiling for Production LLM Systems
- Open Access
- 28 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 465-481
MCon: Building an Elastic Cloud for Android Applications with Framework Consolidation
- 28 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 465-481
Open AccessMCon: Building an Elastic Cloud for Android Applications with Framework Consolidation
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11795-11804
Configuring Dynamic Multi-Stage Serverless Pipelines for Video Processing with Minimal Profiling Overhead
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11795-11804
Open AccessConfiguring Dynamic Multi-Stage Serverless Pipelines for Video Processing with Minimal Profiling Overhead
- 18 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Networking
- Vol. 33 (5) , 2690-2705
A Five-Year Retrospective of Cellular Reliability Evolution: The Encouraging, Disappointing, and Further Enhancements
With recent advances on cellular technologies pushing the boundary of cellular performance, cellular reliability has become a key concern of their adoption and deployment. To fully understand cellular reliability, we work with a major Android phone vendor, Xiaomi, to conduct a long-term (2020-2024) and large-scale (involving 123M users) measurement study in China, with coarse-grained general statistics and fine-grained sampling diagnostics. Our measurement reveals contrasting evolution trends of cellular failures in different stages of the data connection: in the past five years, failures after connection establishment decrease remarkably (by 29%), while failures during connection setup exhibit a sharp increase (by 38%). Our analysis illustrates that the contrast stems from the joint impact of multiple stakeholders, including ISPs’ increasing deployment of 5G base stations, 5G infrastructure upgrade from NSA (Non-Standalone) to SA (Standalone) mode, software defects coming from Android’s adaptation to new cellular technologies, and so forth. Our work provides actionable insights for improving cellular reliability at scale. More importantly, we have built on our insights to develop enhancements that effectively address cellular reliability issues with remarkable real-world impact—our optimizations have reduced 38% cellular connection failures for 5G phones and 31% failure recovery time across all phones.
- 18 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Networking
- Vol. 33 (5) , 2690-2705
A Five-Year Retrospective of Cellular Reliability Evolution: The Encouraging, Disappointing, and Further Enhancements
With recent advances on cellular technologies pushing the boundary of cellular performance, cellular reliability has become a key concern of their adoption and deployment. To fully understand cellular reliability, we work with a major Android phone vendor, Xiaomi, to conduct a long-term (2020-2024) and large-scale (involving 123M users) measurement study in China, with coarse-grained general statistics and fine-grained sampling diagnostics. Our measurement reveals contrasting evolution trends of cellular failures in different stages of the data connection: in the past five years, failures after connection establishment decrease remarkably (by 29%), while failures during connection setup exhibit a sharp increase (by 38%). Our analysis illustrates that the contrast stems from the joint impact of multiple stakeholders, including ISPs’ increasing deployment of 5G base stations, 5G infrastructure upgrade from NSA (Non-Standalone) to SA (Standalone) mode, software defects coming from Android’s adaptation to new cellular technologies, and so forth. Our work provides actionable insights for improving cellular reliability at scale. More importantly, we have built on our insights to develop enhancements that effectively address cellular reliability issues with remarkable real-world impact—our optimizations have reduced 38% cellular connection failures for 5G phones and 31% failure recovery time across all phones.
- Open Access
- 13 April 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
- Vol. 20 (3) , 1-24
Who Should We Blame for Android App Crashes? An In-Depth Study at Scale and Practical Resolutions
Android system has been widely deployed in energy-constrained IoT devices for many practical applications, such as smart phone, smart home, healthcare, fitness, and beacons. However, Android users oftentimes suffer from app crashes, which directly disrupt user experience and could lead to data loss. Till now, the community have limited understanding of their prevalence, characteristics, and root causes. In this article, we make an in-depth study of the crash events regarding ten very popular apps of different genres, based on fine-grained system-level traces crowd-sourced from 93 million Android devices. We find that app crashes occur prevalently on the various hardware models studied, and better hardware does not seem to essentially relieve the problem. Most importantly, we unravel multi-fold root causes of app crashes, and pinpoint that the most crashes stem from the subtle yet crucial inconsistency between app developers’ supposed memory/process management model and Android’s actual implementations. We design practical approaches to addressing the inconsistency; after large-scale deployment, they reduce 40.4% of the app crashes with negligible system overhead. In addition, we summarize important lessons learned from this study, and have released our measurement code/data to the community.
- 13 April 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
- Vol. 20 (3) , 1-24
Open AccessWho Should We Blame for Android App Crashes? An In-Depth Study at Scale and Practical Resolutions
Android system has been widely deployed in energy-constrained IoT devices for many practical applications, such as smart phone, smart home, healthcare, fitness, and beacons. However, Android users oftentimes suffer from app crashes, which directly disrupt user experience and could lead to data loss. Till now, the community have limited understanding of their prevalence, characteristics, and root causes. In this article, we make an in-depth study of the crash events regarding ten very popular apps of different genres, based on fine-grained system-level traces crowd-sourced from 93 million Android devices. We find that app crashes occur prevalently on the various hardware models studied, and better hardware does not seem to essentially relieve the problem. Most importantly, we unravel multi-fold root causes of app crashes, and pinpoint that the most crashes stem from the subtle yet crucial inconsistency between app developers’ supposed memory/process management model and Android’s actual implementations. We design practical approaches to addressing the inconsistency; after large-scale deployment, they reduce 40.4% of the app crashes with negligible system overhead. In addition, we summarize important lessons learned from this study, and have released our measurement code/data to the community.
- Open Access
- 2 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Virtual Device Farms for Mobile App Testing at Scale: A Pursuit for Fidelity, Efficiency, and Accessibility
Virtual devices based on device emulation have been widely used in lab research of mobile app testing for their efficiency and low cost. However, it remains controversial to use virtual devices for app testing in industry, given the inherent difficulties of high-fidelity emulation across diverse mobile systems and devices. Hence, mobile app companies still rely on physical device farms or services like AWS Device Farm. This paper presents our effort to analyze, improve, and effectively use virtual devices for large-scale testing of mobile apps like Douyin. Our goal is to understand the fidelity of virtual devices and to explore how to better utilize virtual devices to improve the efficiency and accessibility of mobile app testing in industrial settings. Our study is conducted on a massive commercial testing infrastructure that deploys a physical device farm and its virtualized counterpart. We show that high-fidelity app testing can be achieved by sensible design and implementation of virtual device farms. With that, we find that major discrepancies are no longer caused by commonly believed factors like hardware heterogeneity and system customizations, but due to non-standard, uncoordinated, and occasionally defective vendor-specific services and drivers, as well as defense mechanisms against malicious app behavior. We present effective solutions to address those problems to significantly improve testing fidelity. We also share our experiences of using virtual device farms to substantially improve the efficiency and accessibility of mobile app testing, without compromising safety.
- 2 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessVirtual Device Farms for Mobile App Testing at Scale: A Pursuit for Fidelity, Efficiency, and Accessibility
Virtual devices based on device emulation have been widely used in lab research of mobile app testing for their efficiency and low cost. However, it remains controversial to use virtual devices for app testing in industry, given the inherent difficulties of high-fidelity emulation across diverse mobile systems and devices. Hence, mobile app companies still rely on physical device farms or services like AWS Device Farm. This paper presents our effort to analyze, improve, and effectively use virtual devices for large-scale testing of mobile apps like Douyin. Our goal is to understand the fidelity of virtual devices and to explore how to better utilize virtual devices to improve the efficiency and accessibility of mobile app testing in industrial settings. Our study is conducted on a massive commercial testing infrastructure that deploys a physical device farm and its virtualized counterpart. We show that high-fidelity app testing can be achieved by sensible design and implementation of virtual device farms. With that, we find that major discrepancies are no longer caused by commonly believed factors like hardware heterogeneity and system customizations, but due to non-standard, uncoordinated, and occasionally defective vendor-specific services and drivers, as well as defense mechanisms against malicious app behavior. We present effective solutions to address those problems to significantly improve testing fidelity. We also share our experiences of using virtual device farms to substantially improve the efficiency and accessibility of mobile app testing, without compromising safety.
- Open Access
- 1 January 2023
- Published by China Engineering Science Press Co. Ltd. in Strategic Study of CAE
- Vol. 25 (6) , 126
Development of Security Protection Technologies for Industrial Control System
Industrial control system; security protection; autonomous and controllable; new security-protection architecture; guard mode
- 1 January 2023
- Published by China Engineering Science Press Co. Ltd. in Strategic Study of CAE
- Vol. 25 (6) , 126
Open AccessDevelopment of Security Protection Technologies for Industrial Control System
Industrial control system; security protection; autonomous and controllable; new security-protection architecture; guard mode
- Open Access
Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation
Federated learning (FL) can be essential in knowledge representation, reasoning, and data mining applications over multi-source knowledge graphs (KGs). A recent study FedE first proposes an FL framework that shares entity embeddings of KGs across all clients. However, entity embedding sharing from FedE would incur a severe privacy leakage. Specifically, the known entity embedding can be used to infer whether a specific relation between two entities exists in a private client. In this paper, we introduce a novel attack method that aims to recover the original data based on the embedding information, which is further used to evaluate the vulnerabilities of FedE. Furthermore, we propose a Federated learning paradigm with privacy-preserving Relation embedding aggregation (FedR) to tackle the privacy issue in FedE. Besides, relation embedding sharing can significantly reduce the communication cost due to its smaller size of queries. We conduct extensive experiments to evaluate FedR with five different KG embedding models and three datasets. Compared to FedE, FedR achieves similar utility and significant improvements regarding privacy-preserving effect and communication efficiency on the link prediction task.
Open AccessEfficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation
Federated learning (FL) can be essential in knowledge representation, reasoning, and data mining applications over multi-source knowledge graphs (KGs). A recent study FedE first proposes an FL framework that shares entity embeddings of KGs across all clients. However, entity embedding sharing from FedE would incur a severe privacy leakage. Specifically, the known entity embedding can be used to infer whether a specific relation between two entities exists in a private client. In this paper, we introduce a novel attack method that aims to recover the original data based on the embedding information, which is further used to evaluate the vulnerabilities of FedE. Furthermore, we propose a Federated learning paradigm with privacy-preserving Relation embedding aggregation (FedR) to tackle the privacy issue in FedE. Besides, relation embedding sharing can significantly reduce the communication cost due to its smaller size of queries. We conduct extensive experiments to evaluate FedR with five different KG embedding models and three datasets. Compared to FedE, FedR achieves similar utility and significant improvements regarding privacy-preserving effect and communication efficiency on the link prediction task.