Song Guo

Song Guo
The Hong Kong Polytechnic University | PolyU · Department of Computing

PhD

About

706
Publications
140,898
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
15,935
Citations
Additional affiliations
August 2016 - present
The Hong Kong Polytechnic University
Position
  • Professor (Full)
October 2007 - August 2016
The University of Aizu
Position
  • Professor (Full)
September 2006 - August 2007
University of Northern British Columbia
Position
  • Professor (Assistant)

Publications

Publications (706)
Preprint
With the rapid development of the Industrial Internet of Things (IIoT), the industrial network provides new challenges in terms of communications, requiring strict latency boundaries and ultra-reliable transmission. Moreover, massive IIoT devices will connect to the industrial network via wired and wireless. Recently, fifth-generation (5G) wireless...
Preprint
The past few years have witnessed an exponential growth of compelling UAVs swarm applications ranging from industrial production, and intelligent transport, to disaster rescue. The high-speed mobility of the UAV swarm leads to a new clan of networks, termed flying ad-hoc networks (FANETs). How to design an effective routing mechanism in such a dyna...
Preprint
Quick global aggregation of effective distributed parameters is crucial to federated learning (FL), which requires adequate bandwidth for parameters communication and sufficient user data for local training. Otherwise, FL may cost excessive training time for convergence and produce inaccurate models. In this paper, we propose a brand-new FL framewo...
Preprint
Federated learning (FL) has emerged as a promising privacy-preserving distributed machine learning framework recently. It aims at collaboratively learning a shared global model by performing distributed training locally on edge devices and aggregating local models into a global one without centralized raw data sharing in the cloud server. However,...
Conference Paper
The space-air-ground (SAG) integrated networks will play a major role in the sixth generation (6G) mobile networks, which will provide global coverage, full connection and pervasive intelligence services for multiple ground Internet of Things (IoT) devices. Moreover, massive computing tasks can be either performed by local devices, or offloaded to...
Preprint
With the vigorous development of artificial intelligence (AI), the intelligent applications based on deep neural network (DNN) change people's lifestyles and the production efficiency. However, the huge amount of computation and data generated from the network edge becomes the major bottleneck, and traditional cloud-based computing mode has been un...
Article
Full-text available
The compelling applications of Low earth orbit (LEO) satellites networks in our daily lives have been witnessed in recent years, ranging from weather forecasts to military monitoring. LEO satellites networks have become a necessary supplement to terrestrial networks aiming to provide worldwide, ubiquitous connectivity, especially in complicated are...
Article
Full-text available
Driven by the burgeoning growth of the Internet of Everything and the substantial breakthroughs in deep learning (DL) algorithms, a booming of artificial intelligence (AI) applications keep emerging. Meanwhile, the advance in existing computing paradigms, i.e., cloud computing and edge computing, provide assorted computing solutions to satisfy the...
Conference Paper
The prevalent personalized federated learning (PFL) usually pursues a trade-off between personalization and generalization by maintaining a shared global model to guide the training process of local models. However, the sole global model may easily transfer deviated context knowledge to some local models when multiple latent contexts exist across t...
Conference Paper
Recent studies have shown that the training samples can be recovered from gradients, which are called Gradient Inversion (GradInv) attacks. However, there remains a lack of extensive surveys covering recent advances and thorough analysis of this issue. In this paper, we present a comprehensive survey on GradInv, aiming to summarize the cutting-edge...
Preprint
The compelling applications of Low earth orbit (LEO) satellites networks in our daily lives have been witnessed in recent years, ranging from weather forecasts to military monitoring. LEO satellite networks have grown in importance as a complement to terrestrial networks aiming at delivering global, ubiquitous communication. However, due to LEO net...
Preprint
Full-text available
Recent researches in artificial intelligence have proposed versatile convolutional neural networks (CNN) with different structures and substantially improved the accuracy of various intelligent applications. Nevertheless, the CNN inference imposes heavy computation overhead on mobile devices, but uploading the large volume of raw data to the cloud...
Preprint
Recent studies have shown that the training samples can be recovered from gradients, which are called Gradient Inversion (GradInv) attacks. However, there remains a lack of extensive surveys covering recent advances and thorough analysis of this issue. In this paper, we present a comprehensive survey on GradInv, aiming to summarize the cutting-edge...
Preprint
Full-text available
Using large batches in recent federated learning studies has improved convergence rates, but it requires additional computation overhead compared to using small batches. To overcome this limitation, we propose a unified framework FedAMD, which disjoints the participants into anchor and miner groups based on time-varying probabilities. Each client i...
Article
Full-text available
Distributed machine learning (ML) was originally introduced to solve a complex ML problem in a parallel way for more efficient usage of computation resources. In recent years, such learning has been extended to satisfy other objectives, namely, performing learning in situ on the training data at multiple locations and keeping the training datasets...
Preprint
Personalized Federated Learning (pFL) not only can capture the common priors from broad range of distributed data, but also support customized models for heterogeneous clients. Researches over the past few years have applied the weighted aggregation manner to produce personalized models, where the weights are determined by calibrating the distance...
Conference Paper
Full-text available
State-of-the-art blockchain sharding solutions, say Monoxide, can induce imbalanced transaction (TX) distributions among all blockchain shards due to their account deployment mechanisms. Imbalanced TX distributions can then cause hot shards, in which the cross-shard TXs may experience an unlimited length of confirmation latency. Thus, how to addres...
Preprint
The compelling applications of Low earth orbit (LEO) satellites networks in our daily lives have been witnessed in recent years, ranging from weather forecasts to military monitoring. LEO satellites networks have become a necessary supplement to terrestrial networks aiming to provide worldwide, ubiquitous connectivity, especially in complicated are...
Article
Full-text available
In the past decade, the Artificial Intelligent & Internet of Things (AIoT) has become a disruptive force reshaping our lives and works. Meanwhile, the significant increase in the number of AIoT devices and the data volume also presents huge challenges for the centralized AI training architecture (e.g., security issues, privacy issues). Recently, wi...
Preprint
Full-text available
Traditional one-bit compressed stochastic gradient descent can not be directly employed in multi-hop all-reduce, a widely adopted distributed training paradigm in network-intensive high-performance computing systems such as public clouds. According to our theoretical findings, due to the cascading compression, the training process has considerable...
Preprint
Multi-label zero-shot learning extends conventional single-label zero-shot learning to a more realistic scenario that aims at recognizing multiple unseen labels of classes for each input sample. Existing works usually exploit attention mechanism to generate the correlation among different labels. However, most of them are usually biased on several...
Preprint
Recently, the enactment of privacy regulations has promoted the rise of machine unlearning paradigm. Most existing studies mainly focus on removing unwanted data samples from a learnt model. Yet we argue that they remove overmuch information of data samples from latent feature space, which is far beyond the sensitive feature scope that genuinely ne...
Article
In Edge Learning, training data are non-independently and identically distributed (non-IID). Applying the same learning strategy for all workers fails to work efficiently. In this chapter, we introduce federated learning, where the training data are always non-IID due to data isolation. Then, we summarize enabling technologies for efficient trainin...
Article
Discover this multi-disciplinary and insightful work, which integrates machine learning, edge computing, and big data. Presents the basics of training machine learning models, key challenges and issues, as well as comprehensive techniques including edge learning algorithms, and system design issues. Describes architectures, frameworks, and key tech...
Article
Conventional distributed machine learning manages the training data in a centralized mode without considering the privacy and security problems during training or inference. With the rapid development and wide deployment of artificial intelligence technology these days, privacy protection has gained more and more attention. Moreover, EL participant...
Book
Discover this multi-disciplinary and insightful work, which integrates machine learning, edge computing, and big data. Presents the basics of training machine learning models, key challenges and issues, as well as comprehensive techniques including edge learning algorithms, and system design issues. Describes architectures, frameworks, and key tech...
Article
Edge learning has enabled the training of large-scale machine learning models on a big dataset by implementing data parallelism in multiple nodes. However, the iterative interaction generated by multiple learning nodes together with the considerable quantity of communication data on each interaction yields huge communication overhead, which greatly...
Article
This chapter first focuses on model compression and hardware acceleration for edge learning. It covers many aspects, including the learning algorithms, learning-oriented communication, distributed machine learning with hardware adaptation, TEE-based privacy protection, algorithm, and hardware joint optimization, etc. The essential objective is to i...
Article
In a cloud-edge environment, data are generated by different types of devices, and these devices have various computation capabilities and storage sizes. It is unrealistic to execute all the tasks in the cloud, instead, putting some work into edge servers that are close to end-users would be more reasonable. Edge Learning is a powerful paradigm for...
Article
Discover this multi-disciplinary and insightful work, which integrates machine learning, edge computing, and big data. Presents the basics of training machine learning models, key challenges and issues, as well as comprehensive techniques including edge learning algorithms, and system design issues. Describes architectures, frameworks, and key tech...
Article
With the growth of model complexity and computational overhead, modern ML applications are usually handled by the distributed systems, where the training procedure is conducted in parallel. Basically, the datasets and models are partitioned to different workers in data parallelism and model parallelism, respectively. In this chapter, we present the...
Article
Discover this multi-disciplinary and insightful work, which integrates machine learning, edge computing, and big data. Presents the basics of training machine learning models, key challenges and issues, as well as comprehensive techniques including edge learning algorithms, and system design issues. Describes architectures, frameworks, and key tech...
Article
Big data and AI are enabling technologies for smart decision-making, automation, and resource optimization. These technologies collectively promote intelligent services from concepts to practical applications. It is widely recognized that Intelligent Services meet the strategic development of emerging industries, meanwhile enrich people’s lifestyle...
Article
Full-text available
This paper studies the PBFT-based sharded permissioned blockchain, which executes in either a local datacenter or a rented cloud platform. In such permissioned blockchain, the transaction (TX) assignment strategy could be malicious such that the network shards may possibly receive imbalanced transactions or even bursty-TX injection attacks. An imba...
Article
Full-text available
The sixth generation mobile networks (6G) will undergo an unprecedented transformation to revolutionize the wireless system evolution from connected things to connected intelligence, where future 6G Industrial Internet of Things (IIoT) covers a range of industrial nodes such as sensors, controllers, and actuators. Additionally, data scattered aroun...
Article
This chapter introduces the background, development history, and typical applications of edge learning. It also specifies the main challenges faced by edge learning from the aspects of data, communication, and computation.
Article
Network slicing has been widely agreed as a promising technique to accommodate diverse services for the Industrial Internet of Things (IIoT). Smart transportation, smart energy, and smart factory/manufacturing are the three key services to form the backbone of IIoT. Network slicing management is of paramount importance in the face of IIoT services...
Article
Mobile Edge Computing (MEC) promises to provide mobile users with delay-sensitive services at the edge of network, and each user service request usually is associated with a Service Function Chain (SFC) requirement that consists of Virtualized Network Functions (VNFs) in order. The satisfaction of a user on his requested service is heavily impacted...
Article
Lip reading can help people with speech disorders to communicate with others and provide them with a new channel to interact with the world. In this paper, we design and implement HearMe , an accurate and real-time lip-reading system built on commercial RFID devices. HearMe can be used to accurately recognize different words in a pre-defined voca...
Article
Vehicular Named Data Networking (V-NDN) is promising to improve the content delivery efficiency in Vehicular Ad Hoc Networks (VANETs). However, the potential broadcast storm caused by Interest packet flooding and return path failures caused by vehicle mobility can significantly degrade the content delivery performance. Existing forwarding strategie...
Article
Full-text available
In this work, we study the problem of \underline{R}obust \underline{S}erver \underline{P}lacement (RSP) for edge computing, \emph{i.e.}, in the presence of uncertain edge server failures, how to determine a server placement strategy to maximize the expected overall workload that can be served by edge servers. We mathematically formulate the RSP pro...
Preprint
Full-text available
In the setting of federated optimization, where a global model is aggregated periodically, step asynchronism occurs when participants conduct model training with fully utilizing their computational resources. It is well acknowledged that step asynchronism leads to objective inconsistency under non-i.i.d. data, which degrades the model accuracy. To...
Article
Driven by the increasing demand of real-time mobile application processing, Multi-access Edge Computing (MEC) has been envisioned as a promising paradigm for pushing computational resources to network edges. In this paper, we investigate an MEC network enabled by Unmanned Aerial Vehicles (UAV), and consider both the multiuser computation offloading...
Article
Driven by the increasing demand of real-time mobile application processing, Multi-access Edge Computing (MEC) has been envisioned as a promising paradigm for pushing computational resources to network edges. In this paper, we investigate an MEC network enabled by Unmanned Aerial Vehicles (UAV), and consider both the multi-user computation offloadin...
Article
Full-text available
A novel paradigm named Wireless Powered Mobile Edge Computing (WP-MEC) emerges recently, which integrates Mobile Edge Computing (MEC) and Wireless Power Transfer (WPT) technologies. It enables mobile clients to both extend their computing capacities by task offloading, and charge from edge servers via energy transmission. Existing studies generally...
Article
Full-text available
Unmanned Aerial Vehicles (UAVs) have been utilized to serve on-ground users with various services, e.g., computing, communication and caching, due to their mobility and flexibility. The main focus of many recent studies on UAVs is to deploy a set of homogeneous UAVs with identical capabilities controlled by one UAV owner/company to provide services...
Article
Mobile Edge Computing (MEC) has emerged as a promising paradigm catering to overwhelming explosions of mobile applications, by offloading the compute-intensive tasks to an MEC network for processing. The surging of deep learning brings new vigor and vitality to shape the prospect of intelligent Internet of Things (IoT), and edge intelligence arises...
Preprint
In recent years, personalized federated learning (pFL) has attracted increasing attention for its potential in dealing with statistical heterogeneity among clients. However, the state-of-the-art pFL methods rely on model parameters aggregation at the server side, which require all models to have the same structure and size, and thus limits the appl...
Preprint
Full-text available
We explore the problem of selectively forgetting categories from trained CNN classification models in the federated learning (FL). Given that the data used for training cannot be accessed globally in FL, our insights probe deep into the internal influence of each channel. Through the visualization of feature maps activated by different channels, we...
Article
Unmanned Aerial Vehicles (UAVs) have been utilized to serve on-ground users with various services, e.g., computing, communication and caching, due to their mobility and flexibility. The main focus of many recent studies on UAVs is to deploy a set of homogeneous UAVs with identical capabilities controlled by one UAV owner/company to provide services...
Preprint
Full-text available
Recently, the boosting growth of computation-heavy applications raises great challenges for the Fifth Generation (5G) and future wireless networks. As responding, the hybrid edge and cloud computing (ECC) system has been expected as a promising solution to handle the increasing computational applications with low-latency and on-demand services of c...
Article
The ever-growing Artificial Intelligence (AI) applications have greatly reshaped our world in many areas, e.g., smart home, computer vision, natural language processing, etc. Behind these applications are usually machine learning (ML) models with extremely large size, which require huge datasets for accurate training to mine the value contained in...
Article
With the development of smart cities, the chimney construction method can no longer meet service needs. It is extremely urgent to build a unified urban brain, and the core issue is data sharing and fusion. Aiming at the problems of data island, data leakage, and high trust cost in the IoT of smart city, a lightweight and trusted sharing mechanism (...
Article
Ubiquitous intelligence has been widely recognized as a critical vision of the future sixth generation (6G) networks, which implies intelligence over the whole network from the core to the edge, including end devices. Nevertheless, fulfilling this vision, particularly the intelligence at the edge, is extremely challenging due to the limited resourc...
Article
The past few years have witnessed an exponential growth of diverse Internet of Things (IoT) devices as well as compelling applications ranging from industrial production, intelligent transport, warehouse logistics to medical care. Dramatic advances in IoT technology not only bring enormous economic opportunities but also challenges (e.g., privacy a...
Article
Federated Learning (FL) is an emerging paradigm through which decentralized devices can collaboratively train a common model. However, a ser