Shiqiang Wang

Shiqiang Wang
IBM Research · Thomas J. Watson Research Center

PhD

About

121
Publications
28,068
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
4,458
Citations
Citations since 2016
95 Research Items
4299 Citations
201620172018201920202021202202004006008001,0001,200
201620172018201920202021202202004006008001,0001,200
201620172018201920202021202202004006008001,0001,200
201620172018201920202021202202004006008001,0001,200
Additional affiliations
April 2016 - present
IBM Research
Position
  • Research Staff Member
October 2011 - November 2015
Imperial College London
Position
  • PhD Student
Education
October 2011 - November 2015
Imperial College London
Field of study
  • Electrical and Electronic Engineering

Publications

Publications (121)
Article
Full-text available
Mobile edge computing is a new cloud computing paradigm which makes use of small-sized edge-clouds to provide real-time services to users. These mobile edge-clouds (MECs) are located in close proximity to users, thus enabling users to seamlessly access applications running on MECs. Due to the co-existence of the core (centralized) cloud, users, and...
Article
Full-text available
Mobile micro-clouds are promising for enabling performance-critical cloud applications. However, one challenge therein is the dynamics at the network edge. In this paper, we study how to place service instances to cope with these dynamics, where multiple users and service instances coexist in the system. Our goal is to find the optimal placement (c...
Article
Full-text available
Emerging technologies and applications including Internet of Things (IoT), social networking, and crowd-sourcing generate large amounts of data at the network edge. Machine learning models are often built from the collected data, to enable the detection, classification, and prediction of future events. Due to bandwidth, storage, and privacy concern...
Article
Full-text available
In mobile edge computing, local edge servers can host cloud-based services, which reduces network overhead and latency but requires service migrations as users move to new locations. It is challenging to make migration decisions optimally because of the uncertainty in such a dynamic cloud environment. In this paper, we formulate the service migrati...
Chapter
Nowadays, devices are equipped with advanced sensors with higher processing and computing capabilities. Besides, widespread Internet availability enables communication among sensing devices that results the generation of vast amounts of data on edge devices to drive Internet-of-Things (IoT), crowdsourcing, and other emerging technologies. The exten...
Preprint
We propose Flexible Vertical Federated Learning (Flex-VFL), a distributed machine algorithm that trains a smooth, non-convex function in a distributed system with vertically partitioned data. We consider a system with several parties that wish to collaboratively learn a global function. Each party holds a local dataset; the datasets have different...
Preprint
Full-text available
This paper presents a sufficient condition for stochastic gradients not to slow down the convergence of Nesterov's accelerated gradient method. The new condition has the strong-growth condition by Schmidt \& Roux as a special case, and it also allows us to (i) model problems with constraints and (ii) design new types of oracles (e.g., oracles for f...
Article
We consider federated learning in tiered communication networks. Our network model consists of a set of silos, each holding a vertical partition of the data. Each silo contains a hub and a set of clients, with the silo’s vertical data shard partitioned horizontally across its clients. We propose Tiered Decentralized Coordinate Descent (TDCD), a com...
Article
Hierarchical SGD (H-SGD) has emerged as a new distributed SGD algorithm for multi-level communication networks. In H-SGD, before each global aggregation, workers send their updated local models to local servers for aggregations. Despite recent research efforts, the effect of local aggregation on global convergence still lacks theoretical understand...
Article
Full-text available
Graph kernels are historically the most widely-used technique for graph classification tasks. However, these methods suffer from limited performance because of the hand-crafted combinatorial features of graphs. In recent years, graph neural networks (GNNs) have become the state-of-the-art method in downstream graph-related tasks due to their superi...
Preprint
We propose Compressed Vertical Federated Learning (C-VFL) for communication-efficient training on vertically partitioned data. In C-VFL, a server and multiple parties collaboratively train a model on their respective features utilizing several local iterations and sharing compressed intermediate results periodically. Our work provides the first the...
Preprint
Federated learning (FL) faces challenges of intermittent client availability and computation/communication efficiency. As a result, only a small subset of clients can participate in FL at a given time. It is important to understand how partial client participation affects convergence, but most existing works have either considered idealized partici...
Article
Full-text available
Federated learning (FL) allows model training from local data collected by edge/mobile devices while preserving data privacy, which has wide applicability to image and vision applications. A challenge is that client devices in FL usually have much more limited computation and communication resources compared to servers in a data center. To overcome...
Preprint
Coresets are small, weighted summaries of larger datasets, aiming at providing provable error bounds for machine learning (ML) tasks while significantly reducing the communication and computation costs. To achieve a better trade-off between ML error bounds and costs, we propose the first framework to incorporate quantization techniques into the pro...
Preprint
Full-text available
Federated learning (FL) is a useful tool in distributed machine learning that utilizes users' local datasets in a privacy-preserving manner. When deploying FL in a constrained wireless environment; however, training models in a time-efficient manner can be a challenging task due to intermittent connectivity of devices, heterogeneous connection qual...
Preprint
Full-text available
Graph kernels are historically the most widely-used technique for graph classification tasks. However, these methods suffer from limited performance because of the hand-crafted combinatorial features of graphs. In recent years, graph neural networks (GNNs) have become the state-of-the-art method in downstream graph-related tasks due to their superi...
Article
We consider the problem of computing the $k$ -means centers for a large high-dimensional dataset in the context of edge-based machine learning, where data sources offload machine learning computation to nearby edge servers. $k$ -Means computation is fundamental to many data analytics, and the capability of computing provably accurate $k$ -mea...
Chapter
In federated learning, the communication link connecting the edge parties with the central aggregator is sometimes bandwidth-limited and can have high network latency. Therefore, there is a critical need to design and deploy communication-efficient distributed training algorithms. In this chapter, we will review two orthogonal communication-efficie...
Preprint
Full-text available
Federated learning (FL) algorithms usually sample a fraction of clients in each round (partial participation) when the number of participants is large and the server's communication bandwidth is limited. Recent works on the convergence analysis of FL have focused on unbiased client sampling, e.g., sampling uniformly at random, which suffers from sl...
Article
Federated learning (FL) is a distributed learning paradigm that enables a large number of mobile devices to collaboratively learn a model under the coordination of a central server without sharing their raw data. Despite its practical efficiency and effectiveness, the iterative on-device learning process (e.g., local computations and global communi...
Preprint
Full-text available
Federated learning (FL) is a distributed learning paradigm that enables a large number of mobile devices to collaboratively learn a model under the coordination of a central server without sharing their raw data. Despite its practical efficiency and effectiveness, the iterative on-device learning process (e.g., local computations and global communi...
Preprint
We consider federated learning in tiered communication networks. Our network model consists of a set of silos, each holding a vertical partition of the data. Each silo contains a hub and a set of clients, with the silo's vertical data shard partitioned horizontally across its clients. We propose Tiered Decentralized Coordinate Descent (TDCD), a com...
Article
Federated learning (FL) is a distributed machine learning strategy that generates a global model by learning from multiple decentralized edge clients. FL enables on-device training, keeping the client’s local data private, and further, updating the global model based on the local model updates. While FL methods offer several advantages, including s...
Article
Mobile Edge Computing (MEC) is promising for computation-intensive applications (such as automatic and cooperative driving) and storage burdens (video caching) on the Internet of Vehicles (IoV). It paves the way for the establishment of intelligent transportation systems and smart cities. Many countries all over the world have devoted themselves to...
Article
The computational complexity of deep neural networks is a major obstacle of many application scenarios driven by low-power devices, including federated learning. A recent finding shows that random sketches can substantially reduce the model complexity without affecting prediction accuracy. Link to full paper: https://rdcu.be/chtQF
Preprint
Full-text available
We consider the problem of computing the k-means centers for a large high-dimensional dataset in the context of edge-based machine learning, where data sources offload machine learning computation to nearby edge servers. k-Means computation is fundamental to many data analytics, and the capability of computing provably accurate k-means centers by l...
Preprint
Full-text available
Kubernetes (k8s) has the potential to merge the distributed edge and the cloud but lacks a scheduling framework specifically for edge-cloud systems. Besides, the hierarchical distribution of heterogeneous resources and the complex dependencies among requests and resources make the modeling and scheduling of k8s-oriented edge-cloud systems particula...
Preprint
Full-text available
Federated learning (FL) is a distributed learning paradigm that enables a large number of devices to collaboratively learn a model without sharing their raw data. Despite its practical efficiency and effectiveness, the iterative on-device learning process incurs a considerable cost in terms of learning time and energy consumption, which depends cru...
Article
Full-text available
Mobile edge computing provides the opportunity for wireless users to exploit the power of cloud computing without a large communication delay. To serve data-intensive applications (e.g., video analytics, machine learning tasks) from the edge, we need, in addition to computation resources, storage resources for storing server code and data as well a...
Preprint
Full-text available
Knowledge distillation (KD) has enabled remarkable progress in model compression and knowledge transfer. However, KD requires a large volume of original data or their representation statistics that are not usually available in practice. Data-free KD has recently been proposed to resolve this problem, wherein teacher and student models are fed by a...
Preprint
Federated learning is an effective approach to realize collaborative learning among edge devices without exchanging raw data. In practice, these devices may connect to local hubs which are then connected to the global server (aggregator). Due to the (possibly limited) computation capability of these local hubs, it is reasonable to assume that they...
Preprint
Full-text available
In this paper, we provide a rigorous theoretical investigation of an online learning version of the Facility Location problem which is motivated by emerging problems in real-world applications. In our formulation, we are given a set of sites and an online sequence of user requests. At each trial, the learner selects a subset of sites and then incur...
Preprint
Full-text available
Distributed machine learning generally aims at training a global model based on distributed data without collecting all the data to a centralized location, where two different approaches have been proposed: collecting and aggregating local models (federated learning) and collecting and training over representative data summaries (coreset). While ea...
Article
Full-text available
Coreset, which is a summary of the original dataset in the form of a small weighted set in the same sample space, provides a promising approach to enable machine learning over distributed data. Although viewed as a proxy of the original dataset, each coreset is only designed to approximate the cost function of a specific machine learning problem, a...
Article
Full-text available
The rapid development of network function virtualization (NFV) enables a communication network to provide in-network services using virtual network functions (VNFs) deployed on general IT hardware. While existing studies on NFV focused on how to provision VNFs from the provider's perspective, little is done about how to validate the provisioned res...
Conference Paper
Full-text available
Edge computing and Federated Learning (FL) can work in tandem to address issues related to privacy and collaborative distributed learning in untrusted IoT environments. However, deployment of FL in resource-constrained IoT devices faces challenges including asynchronous participation of such devices in training, and the need to prevent malicious de...
Article
Edge computing and Federated Learning (FL) can work in tandem to address issues related to privacy and collaborative distributed learning in untrusted IoT environments. However, deployment of FL in resource-constrained IoT devices faces challenges including asynchronous participation of such devices in training, and the need to prevent malicious de...
Preprint
Full-text available
Nowadays, devices are equipped with advanced sensors with higher processing/computing capabilities. Further, widespread Internet availability enables communication among sensing devices. As a result, vast amounts of data are generated on edge devices to drive Internet-of-Things (IoT), crowdsourcing, and other emerging technologies. The collected ex...
Preprint
Full-text available
We study the problem of augmenting online algorithms with machine learned (ML) predictions. In particular, we consider the \emph{multi-shop ski rental} (MSSR) problem, which is a generalization of the classical ski rental problem. In MSSR, each shop has different prices for buying and renting a pair of skis, and a skier has to make decisions on whe...
Preprint
Full-text available
Many image and vision applications require a large amount of data for model training. Collecting all such data at a central location can be challenging due to data privacy and communication bandwidth restrictions. Federated learning is an effective way of training a machine learning model in a distributed manner from local data collected by client...
Preprint
Full-text available
Federated learning (FL) is an emerging technique for training machine learning models using geographically dispersed data collected by local entities. It includes local computation and synchronization steps. To reduce the communication overhead and improve the overall efficiency of FL, gradient sparsification (GS) can be applied, where instead of t...
Conference Paper
Full-text available
Acoustic signals contain rich information of the environment. They can be used for detecting anomalous events such as in automated machine monitoring. In this demonstration, we present our acoustic anomaly detection system that captures acoustic signals and classifies them using machine learning techniques. Our system includes a server for sound ma...
Conference Paper
Full-text available
Smart speakers have been recently adopted and widely used in consumer homes, largely as a communication interface between human and machines. In addition, these speakers can be used to monitor sounds other than human voice, for example, to watch over elderly people living alone, and to notify if there are changes in their usual activities that may...
Conference Paper
Full-text available
Professional tennis is a fast-paced sport with serves and hits that can reach speeds of over 100 mph and matches lasting long in duration. For example, in 13 years of Grand Slam data, there were 454 matches with an average of 3 sets that lasted 40 minutes. The fast pace and long duration of tennis matches make tracking the time boundaries of each t...
Preprint
Full-text available
Federated learning is a recent approach for distributed model training without sharing the raw data of clients. It allows model training using the large amount of user data collected by edge and mobile devices, while preserving data privacy. A challenge in federated learning is that the devices usually have much lower computational power and commun...
Preprint
Full-text available
Devices at the edge of wireless networks are the last mile data sources for machine learning (ML). As opposed to traditional ready-made public datasets, these user-generated private datasets reflect the freshest local environments in real time. They are thus indispensable for enabling mission-critical intelligent systems, ranging from fog radio acc...