Vladimir Vlassov

Vladimir Vlassov

Auto-generated profile, based on publicly available information

Vladimir Vlassov

KTH Royal Institute of Technology Sweden

Research Focus & Metrics

Academic Career Length

31Years (1996-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 2023 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
Ashish RauniyarAshish Rauniyar
Ashish Rauniyar
DHDesta Haileselassie Hagos
Desta Haileselassie Hagos
Debesh JhaDebesh Jha
Debesh Jha
JHJan Erik Håkegård
Jan Erik Håkegård
UBUlas Bagci
Ulas Bagci
VVVladimir Vlassov
Vladimir Vlassov
With the advent of the Internet of Things (IoT), artificial intelligence (AI), machine learning (ML), and deep learning (DL) algorithms, the landscape of data-driven medical applications has emerged as a promising avenue for designing robust and scalable diagnostic and prognostic models from medical data. This has gained a lot of attention from both academia and industry, leading to significant improvements in healthcare quality. However, the adoption of AI-driven medical applications still faces tough challenges, including meeting security, privacy, and Quality-of-Service (QoS) standards. Recent developments in federated learning (FL) have made it possible to train complex machine-learned models in a distributed manner and have become an active research domain, particularly processing the medical data at the edge of the network in a decentralized way to preserve privacy and address security concerns. To this end, in this article, we explore the present and future of FL technology in medical applications where data sharing is a significant challenge. We delve into the current research trends and their outcomes, unraveling the complexities of designing reliable and scalable FL models. This article outlines the fundamental statistical issues in FL, tackles device-related problems, addresses security challenges, and navigates the complexity of privacy concerns, all while highlighting its transformative potential in the medical field. Our study primarily focuses on medical applications of FL, particularly in the context of global cancer diagnosis. We highlight the potential of FL to enable computer-aided diagnosis tools that address this challenge with greater effectiveness than traditional data-driven methods. Recent literature has shown that FL models are robust and generalize well to new data, which is essential for medical applications. We hope that this comprehensive review will serve as a checkpoint for the field, summarizing the current state of the art and identifying open problems and future research directions.

1 December 2018
Verified
Conference Paper
Closed access
KSKonstantin Sozinov
Konstantin Sozinov
VVVladimir Vlassov
Vladimir Vlassov
SGSarunas Girdzijauskas
Sarunas Girdzijauskas
State-of-the-art deep learning models for human activity recognition use large amount of sensor data to achieve high accuracy. However, training of such models in a data center using data collected from smart devices leads to high communication costs and possible privacy infringement. In order to mitigate aforementioned issues, federated learning can be employed to train a generic classifier by combining multiple local models trained on data originating from multiple clients. In this work we evaluate federated learning to train a human activity recognition classifier and compare its performance to centralized learning by building two models, namely a deep neural network and a softmax regression trained on both synthetic and real-world datasets. We study communication costs as well as the influence of erroneous clients with corrupted data in federated learning setting. We have found that federated learning for the task of human activity recognition is capable of producing models with slightly worse, but acceptable, accuracy compared to centralized models. In our experiments federated learning achieved an accuracy of up to 89% compared to 93% in centralized training for the deep neural network. The global model trained with federated learning on skewed datasets achieves accuracy comparable to centralized learning. Furthermore, we identified an important issue of clients with corrupted data and proposed a federated learning algorithm that identifies and rejects erroneous clients. Lastly, we have identified a trade-off between communication cost and the complexity of a model. We show that more complex models such as deep neural network require more communication in federated learning settings for human activity recognition compared to less complex models, such as multinomial logistic regression.

1 August 2007 in Future Generation Computer Systems
Verified
Journal Article
Closed access
Paolo TrunfioPaolo Trunfio
Paolo Trunfio
Domenico TaliaDomenico Talia
Domenico Talia
HPHarris Papadakis
Harris Papadakis
PFP. Fragopoulou
P. Fragopoulou
MMMatteo Mordacchini
Matteo Mordacchini
SHS. Haridi
S. Haridi

1 October 2016
Verified
Conference Paper
Closed access
HSHooman Peiro Sajjad
Hooman Peiro Sajjad
KDKen Danniswara
Ken Danniswara
AAAhmad Al-Shishtawy
Ahmad Al-Shishtawy
VVVladimir Vlassov
Vladimir Vlassov
In stream processing, data is streamed as a continuous flow of data items, which are generated from multiple sources and geographical locations. The common approach for stream processing is to transfer raw data streams to a central data center that entails communication over the wide-area network (WAN). However, this approach is inefficient and falls short for two main reasons: (i) the burst in the amount of data generated at the network edge by an increasing number of connected devices, (ii) the emergence of applications with predictable and low latency requirements. In this paper, we propose SpanEdge, a novel approach that unifies stream processing across a geo-distributed infrastructure, including the central and near-the-edge data centers. SpanEdge reduces or eliminates the latency incurred by WAN links by distributing stream processing applications across the central and the near-the-edge data centers. Furthermore, SpanEdge provides a programming environment, which allows programmers to specify parts of their applications that need to be close to the data source. Programmers can develop a stream processing application, regardless of the number of data sources and their geographical distributions. As a proof of concept, we implemented and evaluated a prototype of SpanEdge. Our results show that SpanEdge can optimally deploy the stream processing applications in a geo-distributed infrastructure, which significantly reduces the bandwidth consumption and the response latency.

1 July 2018 in Proceedings of the VLDB Endowment
Verified
Journal Article
Open access
PDF file
ZAZainab Abbas
Zainab Abbas
VKVasiliki Kalavri
Vasiliki Kalavri
PCParis Carbone
Paris Carbone
VVVladimir Vlassov
Vladimir Vlassov
Graph partitioning is an essential yet challenging task for massive graph analysis in distributed computing. Common graph partitioning methods scan the complete graph to obtain structural characteristics offline, before partitioning. However, the emerging need for low-latency, continuous graph analysis led to the development of online partitioning methods. Online methods ingest edges or vertices as a stream, making partitioning decisions on the fly based on partial knowledge of the graph. Prior studies have compared offline graph partitioning techniques across different systems. Yet, little effort has been put into investigating the characteristics of online graph partitioning strategies. In this work, we describe and categorize online graph partitioning techniques based on their assumptions, objectives and costs. Furthermore, we employ an experimental comparison across different applications and datasets, using a unified distributed runtime based on Apache Flink. Our experimental results showcase that model-dependent online partitioning techniques such as low-cut algorithms offer better performance for communication-intensive applications such as bulk synchronous iterative algorithms, albeit higher partitioning costs. Otherwise, model-agnostic techniques trade off data locality for lower partitioning costs and balanced workloads which is beneficial when executing data-parallel single-pass graph algorithms.

12 October 2017 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
VKVasiliki Kalavri
Vasiliki Kalavri
VVVladimir Vlassov
Vladimir Vlassov
SHSeif Haridi
Seif Haridi
Efficient processing of large-scale graphs in distributed environments has been an increasingly popular topic of research in recent years. Inter-connected data that can be modeled as graphs arise in application domains such as machine learning, recommendation, web search, and social network analysis. Writing distributed graph applications is inherently hard and requires programming models that can cover a diverse set of problem domains, including iterative refinement algorithms, graph transformations, graph aggregations, pattern matching, ego-network analysis, and graph traversals. Several high-level programming abstractions have been proposed and adopted by distributed graph processing systems and big data platforms. Even though significant work has been done to experimentally compare distributed graph processing frameworks, no qualitative study and comparison of graph programming abstractions has been conducted yet. In this survey, we review and analyze the most prevalent high-level programming models for distributed graph processing, in terms of their semantics and applicability. We review 34 distributed graph processing systems with respect to the graph processing models they implement and we survey applications that appear in recent distributed graph systems papers. Finally, we discuss trends and open research questions in the area of distributed graph processing.