Zhaowu Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhaowu Huang has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Fang Dong
Southeast University, Nanjing, China
9 shared publications - Dian Shen
Southeast University, Nanjing, China
4 shared publications - Xiaolin Guo
School of Computer Science and Engineering, Southeast University, Nanjing, China
4 shared publications - Jinghui Zhang
Southeast University, Nanjing, China
3 shared publications - Daheng Yin
Simon Fraser University, Burnaby, British Columbia, Canada
2 shared publications - Jiangchuan Liu
Simon Fraser University, Burnaby, Canada
2 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 19286-19303
AccSI: Accelerating Serverless Inference via Edge-Assisted Pipelined Model Fetching
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 19286-19303
AccSI: Accelerating Serverless Inference via Edge-Assisted Pipelined Model Fetching
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
CAGS: Color-Adaptive Volumetric Video Streaming with Dynamic 3D Gaussian Splatting
Volumetric video (VV) streaming delivers truly immersive viewing experiences over the Internet, serving as a critical foundation for next-generation applications, including immersive telepresence in the metaverse, the surveillance of remote ecological systems, and robotic teleoperation for embodied AI, and beyond. Beyond immersive viewing, these applications turn VV streaming into a real-time interface to remote physical environments, imposing new system-level demands for photorealistic scene representation, low-latency interaction, and robust performance under heterogeneous network conditions. 3D Gaussian Splatting (3DGS) has been widely used for real-time photorealistic rendering, offering superior visual quality and rendering performance, but it faces challenges due to bandwidth consumption. Furthermore, as the foundation of adaptive VV streaming, existing Levels of Detail (LoD) methods based on density are not well-suited to Gaussian representations, leading to visible gaps and severe quality degradation. Recent studies have also explored attribute compression techniques to reduce bandwidth consumption. Our preliminary studies reveal that aggressive attribute compression primarily causes color distortion, which can be effectively corrected in the rendered image using a reference image. Motivated by these findings, we propose a novel Color-Adaptive scheme for adaptive VV streaming that uses vector quantization (VQ) to establish LoDs and correct color distortions with low-resolution reference images. We further present CAGS, an adaptive VV streaming system compatible with diverse Gaussian representations, which integrates the Color-Adaptive scheme by rendering reference images on the streaming server and performing color restoration on the client. Extensive experiments on our prototype system demonstrate that CAGS outperforms the existing adaptive streaming systems in PSNR by 5 ∼ 20 dB under fluctuating bandwidth, operates significantly faster than existing scalable Gaussian compression methods, and generalizes across different Gaussian representations. The code is available at https://github.com/yindaheng98/ColorAdaptiveGaussianSplatting.
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessCAGS: Color-Adaptive Volumetric Video Streaming with Dynamic 3D Gaussian Splatting
Volumetric video (VV) streaming delivers truly immersive viewing experiences over the Internet, serving as a critical foundation for next-generation applications, including immersive telepresence in the metaverse, the surveillance of remote ecological systems, and robotic teleoperation for embodied AI, and beyond. Beyond immersive viewing, these applications turn VV streaming into a real-time interface to remote physical environments, imposing new system-level demands for photorealistic scene representation, low-latency interaction, and robust performance under heterogeneous network conditions. 3D Gaussian Splatting (3DGS) has been widely used for real-time photorealistic rendering, offering superior visual quality and rendering performance, but it faces challenges due to bandwidth consumption. Furthermore, as the foundation of adaptive VV streaming, existing Levels of Detail (LoD) methods based on density are not well-suited to Gaussian representations, leading to visible gaps and severe quality degradation. Recent studies have also explored attribute compression techniques to reduce bandwidth consumption. Our preliminary studies reveal that aggressive attribute compression primarily causes color distortion, which can be effectively corrected in the rendered image using a reference image. Motivated by these findings, we propose a novel Color-Adaptive scheme for adaptive VV streaming that uses vector quantization (VQ) to establish LoDs and correct color distortions with low-resolution reference images. We further present CAGS, an adaptive VV streaming system compatible with diverse Gaussian representations, which integrates the Color-Adaptive scheme by rendering reference images on the streaming server and performing color restoration on the client. Extensive experiments on our prototype system demonstrate that CAGS outperforms the existing adaptive streaming systems in PSNR by 5 ∼ 20 dB under fluctuating bandwidth, operates significantly faster than existing scalable Gaussian compression methods, and generalizes across different Gaussian representations. The code is available at https://github.com/yindaheng98/ColorAdaptiveGaussianSplatting.
- 14 January 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 336
Adaptive region encoding for efficient video object detection in edge computing
- 14 January 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 336
Adaptive region encoding for efficient video object detection in edge computing
- 21 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (5) , 6277-6291
Popularity-Aware Layer-Wise Caching and Function Scheduling for Dynamic Workflow at the Edge
Serverless Edge Computing (SEC) has emerged as a promising paradigm for delivering low-latency, resource-efficient services for edge-native applications, which are implemented as dependent functions, forming Directed Acyclic Graph (DAG) workflows. Unfortunately, the application’s performance is hindered by the notorious issue of cold startup, especially in resource-constrained SEC environments. Layer-wise container caching has been proven to be an effective startup acceleration solution in SEC, due to its fine granularity and flexibility. However, due to the dynamic nature of call graphs and the skewness in function popularity in DAG workflows, as well as the heterogeneity of container layer cold start time and edge computing environments, the performance of existing layer-wise caching mechanisms degrades significantly. To solve this problem, we propose an efficient DAG workflow deployment method in SEC to minimize the application completion time (ACT) in the long term. We model the problem as a joint optimization of container layer-wise caching and function scheduling, which is a Time-coupled Integer Nonlinear Programming (TINLP) problem. To solve it, we first convert it to an Integer Linear Programming (ILP) problem and propose an online algorithm with theoretical performance guarantees. Extensive experiments demonstrate that our method achieves up to$2.92\times$ speedup in ACT reduction.- 21 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (5) , 6277-6291
Popularity-Aware Layer-Wise Caching and Function Scheduling for Dynamic Workflow at the Edge
Serverless Edge Computing (SEC) has emerged as a promising paradigm for delivering low-latency, resource-efficient services for edge-native applications, which are implemented as dependent functions, forming Directed Acyclic Graph (DAG) workflows. Unfortunately, the application’s performance is hindered by the notorious issue of cold startup, especially in resource-constrained SEC environments. Layer-wise container caching has been proven to be an effective startup acceleration solution in SEC, due to its fine granularity and flexibility. However, due to the dynamic nature of call graphs and the skewness in function popularity in DAG workflows, as well as the heterogeneity of container layer cold start time and edge computing environments, the performance of existing layer-wise caching mechanisms degrades significantly. To solve this problem, we propose an efficient DAG workflow deployment method in SEC to minimize the application completion time (ACT) in the long term. We model the problem as a joint optimization of container layer-wise caching and function scheduling, which is a Time-coupled Integer Nonlinear Programming (TINLP) problem. To solve it, we first convert it to an Integer Linear Programming (ILP) problem and propose an online algorithm with theoretical performance guarantees. Extensive experiments demonstrate that our method achieves up to$2.92\times$ speedup in ACT reduction.- 11 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (5) , 3650-3666
Resource-Efficient DNN Inference With Early Exiting in Serverless Edge Computing
Serverless Edge Computing (SEC) has gained widespread adoption in improving resource utilization due to its triggered event-driven model. However, deploying deep neural network (DNN) inference services directly in SEC leads to resource inefficiencies, which stem from two key factors. Firstly, existing methods adopt model-wise function encapsulation, which requires the entire DNN model to occupy memory throughout its execution lifecycle. This increases both memory footprint and occupancy time. Secondly, uniform DNN inference for diversity input leads to redundant computations and additional inference time. To this end, we propose REDI, a novel framework that leverages fine-grained block-wise function encapsulation and progressive inference to provide resource-efficient DNN inference while ensuring latency requirements. REDI enables the release of memory from already inferred shallow networks and allows each request to exit early based on input data complexity, eliminating redundant computations. To fully unleash the potential, REDI jointly considers resource heterogeneity, data diversity, and environment dynamics to investigate the block-wise function placement problem. We introduce an uncertainty-aware online learning-driven algorithm with bounded regret. Finally, we conduct extensive trace-driven experiments to evaluate our methods, demonstrating that REDI achieves a significant speedup of up to $6.52\times$ in terms of resource usage cost compared to state-of-the-art methods.
- 11 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (5) , 3650-3666
Resource-Efficient DNN Inference With Early Exiting in Serverless Edge Computing
Serverless Edge Computing (SEC) has gained widespread adoption in improving resource utilization due to its triggered event-driven model. However, deploying deep neural network (DNN) inference services directly in SEC leads to resource inefficiencies, which stem from two key factors. Firstly, existing methods adopt model-wise function encapsulation, which requires the entire DNN model to occupy memory throughout its execution lifecycle. This increases both memory footprint and occupancy time. Secondly, uniform DNN inference for diversity input leads to redundant computations and additional inference time. To this end, we propose REDI, a novel framework that leverages fine-grained block-wise function encapsulation and progressive inference to provide resource-efficient DNN inference while ensuring latency requirements. REDI enables the release of memory from already inferred shallow networks and allows each request to exit early based on input data complexity, eliminating redundant computations. To fully unleash the potential, REDI jointly considers resource heterogeneity, data diversity, and environment dynamics to investigate the block-wise function placement problem. We introduce an uncertainty-aware online learning-driven algorithm with bounded regret. Finally, we conduct extensive trace-driven experiments to evaluate our methods, demonstrating that REDI achieves a significant speedup of up to $6.52\times$ in terms of resource usage cost compared to state-of-the-art methods.
- 12 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (6) , 7434-7445
ADPTD: Adaptive Data Partition With Unbiased Task Dispatching for Video Analytics at the Edge
Recently, edge-assisted methods have been proposed as a promising technique to deliver fast and accurate on-device video analytics by partitioning frame data and dispatching them to edge servers for parallel execution. However, the data partition reduces the detection latency but decreases accuracy since objects may cross the boundaries of adjacent blocks. The effect of data partition on the accuracy and latency depends on multiple vital parameters (e.g., target size, density, network, and computing resources.) in an unknown and time-varying fashion. Moreover, these parameters are determined by the application scenarios and edge environment, which are uncertain and heterogeneous at the edge. Hence, how to partition frames to strike a balance between accuracy and latency is a non-trivial and intractable problem. To this end, we propose an online learning-based device-edge-cloud collaboration framework, ADPTD, to guide data partition at the edge. We propose an optimal task dispatching algorithm (OTD) to minimize detection latency. Then, we propose a multi-armed bandit-based algorithm to pick a data partition strategy and invoke OTD to dispatch tasks in each time slot. Theoretical analysis reveals that ADPTD achieves sublinear regret. Extensive experimental results show that ADPTD outperforms the state-of-the-art methods, achieving a latency reduction of up to 2.53× and improving accuracy by up to 49.4%.
- 12 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (6) , 7434-7445
ADPTD: Adaptive Data Partition With Unbiased Task Dispatching for Video Analytics at the Edge
Recently, edge-assisted methods have been proposed as a promising technique to deliver fast and accurate on-device video analytics by partitioning frame data and dispatching them to edge servers for parallel execution. However, the data partition reduces the detection latency but decreases accuracy since objects may cross the boundaries of adjacent blocks. The effect of data partition on the accuracy and latency depends on multiple vital parameters (e.g., target size, density, network, and computing resources.) in an unknown and time-varying fashion. Moreover, these parameters are determined by the application scenarios and edge environment, which are uncertain and heterogeneous at the edge. Hence, how to partition frames to strike a balance between accuracy and latency is a non-trivial and intractable problem. To this end, we propose an online learning-based device-edge-cloud collaboration framework, ADPTD, to guide data partition at the edge. We propose an optimal task dispatching algorithm (OTD) to minimize detection latency. Then, we propose a multi-armed bandit-based algorithm to pick a data partition strategy and invoke OTD to dispatch tasks in each time slot. Theoretical analysis reveals that ADPTD achieves sublinear regret. Extensive experimental results show that ADPTD outperforms the state-of-the-art methods, achieving a latency reduction of up to 2.53× and improving accuracy by up to 49.4%.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 11089-11098
FSVFG: Towards Immersive Full-Scene Volumetric Video Streaming with Adaptive Feature Grid
Given the truly immersive viewing experiences, full-scene volumetric videos have received increasing attention from both academia and industry. Their vast data volumes, however, present significant challenges for real-time streaming over today's bandwidth-limited Internet. Considering the vast amount of full-scene volumetric data to be streamed and the limited bandwidth on the Internet, achieving adaptive full-scene volumetric video streaming over the Internet presents a significant challenge. Inspired by the advantages offered by neural fields, especially the feature grid method, we propose FSVFG, a novel full-scene volumetric video streaming system integrated feature grids as the representation of volumetric content. FSVFG employs an incremental training approach for feature grids and stores the features and residuals between adjacent grids as frames. To support adaptive streaming, we delve into the data structure and rendering processes of feature grids and propose bandwidth adaptation mechanisms. The mechanisms involve a coarse ray-marching for the selection of features and residuals to be sent, and achieve variable bitrate streaming by Level-of-Detail (LoD) and residual filtering. Based on these mechanisms, FSVFG achieves adaptive streaming by adaptively balancing the transmission of feature and residual according to the available bandwidth. Our preliminary results demonstrate the effectiveness of FSVFG, demonstrating its ability to improve visual quality and reduce bandwidth requirements of full-scene volumetric video streaming.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 11089-11098
Open AccessFSVFG: Towards Immersive Full-Scene Volumetric Video Streaming with Adaptive Feature Grid
Given the truly immersive viewing experiences, full-scene volumetric videos have received increasing attention from both academia and industry. Their vast data volumes, however, present significant challenges for real-time streaming over today's bandwidth-limited Internet. Considering the vast amount of full-scene volumetric data to be streamed and the limited bandwidth on the Internet, achieving adaptive full-scene volumetric video streaming over the Internet presents a significant challenge. Inspired by the advantages offered by neural fields, especially the feature grid method, we propose FSVFG, a novel full-scene volumetric video streaming system integrated feature grids as the representation of volumetric content. FSVFG employs an incremental training approach for feature grids and stores the features and residuals between adjacent grids as frames. To support adaptive streaming, we delve into the data structure and rendering processes of feature grids and propose bandwidth adaptation mechanisms. The mechanisms involve a coarse ray-marching for the selection of features and residuals to be sent, and achieve variable bitrate streaming by Level-of-Detail (LoD) and residual filtering. Based on these mechanisms, FSVFG achieves adaptive streaming by adaptively balancing the transmission of feature and residual according to the available bandwidth. Our preliminary results demonstrate the effectiveness of FSVFG, demonstrating its ability to improve visual quality and reduce bandwidth requirements of full-scene volumetric video streaming.
- 19 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 17 (1) , 251-262
Joint Optimization of Device Selection and Resource Allocation for Multiple Federations in Federated Edge Learning
Federated edge learning (FEEL) is a promising collaborative paradigm, which employs edge devices (EDs) to train machine learning models for a federation. It opens countless opportunities to enable edge intelligence. The increasingly diversified demands for intelligent services are driving the deployment of various federations at the edge. Existing works on FEEL focus on a single federation and ignore inter-federation device competition and intra-device resource allocation, which hinders the applications of FEEL. To address this issue, this article first investigates the bottlenecks of executing multiple federations and builds a joint optimization model as a two-stage Stackelberg game involving device selection and resource allocation. To tackle the problem efficiently, we present a game-theoretical approach named D evice S election and R esource A llocation for M ultiple F ederations G ame (DSRAMF-G). First, following the arbitrary device selection of leaders (i.e., federations), the time cost minimization of followers (i.e., EDs) is modeled as a convex problem to obtain the optimal resource allocation. Then, based on followers' optimal responses, device selection is modeled as a congestion game. We prove the existence of the Nash equilibrium and propose a decentralized mechanism. Finally, extensive experiments show that DSRAMF-G significantly outperforms the state-of-the-art methods, achieving up to 5.9x training speedup and 2.8x resource-savings.
- 19 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 17 (1) , 251-262
Joint Optimization of Device Selection and Resource Allocation for Multiple Federations in Federated Edge Learning
Federated edge learning (FEEL) is a promising collaborative paradigm, which employs edge devices (EDs) to train machine learning models for a federation. It opens countless opportunities to enable edge intelligence. The increasingly diversified demands for intelligent services are driving the deployment of various federations at the edge. Existing works on FEEL focus on a single federation and ignore inter-federation device competition and intra-device resource allocation, which hinders the applications of FEEL. To address this issue, this article first investigates the bottlenecks of executing multiple federations and builds a joint optimization model as a two-stage Stackelberg game involving device selection and resource allocation. To tackle the problem efficiently, we present a game-theoretical approach named D evice S election and R esource A llocation for M ultiple F ederations G ame (DSRAMF-G). First, following the arbitrary device selection of leaders (i.e., federations), the time cost minimization of followers (i.e., EDs) is modeled as a convex problem to obtain the optimal resource allocation. Then, based on followers' optimal responses, device selection is modeled as a congestion game. We prove the existence of the Nash equilibrium and propose a decentralized mechanism. Finally, extensive experiments show that DSRAMF-G significantly outperforms the state-of-the-art methods, achieving up to 5.9x training speedup and 2.8x resource-savings.
- Open Access
- 28 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 67-68
Enabling Adaptive Task Dispatching for Real-time Video Analytics in Uncertain Edge Environments
Recently the edge-assisted method has been proposed as a promising technique to deliver fast video analytics by partitioning frames into multiple blocks for parallel execution in edge servers. However, the problem of dispatching tasks over edge servers becomes challenging in uncertain edge environments provided by different operators, considering that resource availability is not prior knowledge and changes in unpredictable ways. This paper proposes an Adaptive Task Dispatching Scheme (ATDS) for coping with the above problems. We formulate the task dispatching problem as an online learning problem with personalized goals. We propose a Multi-armed bandit-based algorithm to solve it. Simulation results show the effectiveness of the proposed method.
- 28 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 67-68
Open AccessEnabling Adaptive Task Dispatching for Real-time Video Analytics in Uncertain Edge Environments
Recently the edge-assisted method has been proposed as a promising technique to deliver fast video analytics by partitioning frames into multiple blocks for parallel execution in edge servers. However, the problem of dispatching tasks over edge servers becomes challenging in uncertain edge environments provided by different operators, considering that resource availability is not prior knowledge and changes in unpredictable ways. This paper proposes an Adaptive Task Dispatching Scheme (ATDS) for coping with the above problems. We formulate the task dispatching problem as an online learning problem with personalized goals. We propose a Multi-armed bandit-based algorithm to solve it. Simulation results show the effectiveness of the proposed method.