Change search
Link to record
Permanent link

Direct link
BETA
Alternative names
Publications (10 of 10) Show all publications
Kefato, Z., Sheikh, N., Bahri, L., Soliman, A., Girdzijauskas, S. & Montresor, A. (2018). CAS2VEC: Network-Agnostic Cascade Prediction in Online Social Networks. In: The 5th International Symposium on Social Networks Analysis, Management and Security (SNAMS-2018): . Paper presented at The 5th International Symposium on Social Networks Analysis, Management and Security (SNAMS-2018). IEEE
Open this publication in new window or tab >>CAS2VEC: Network-Agnostic Cascade Prediction in Online Social Networks
Show others...
2018 (English)In: The 5th International Symposium on Social Networks Analysis, Management and Security (SNAMS-2018), IEEE, 2018Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
IEEE, 2018
National Category
Computer Systems
Identifiers
urn:nbn:se:kth:diva-239542 (URN)2-s2.0-85060045802 (Scopus ID)
Conference
The 5th International Symposium on Social Networks Analysis, Management and Security (SNAMS-2018)
Note

QC 20181130

Available from: 2018-11-26 Created: 2018-11-26 Last updated: 2019-06-26Bibliographically approved
Kefato, Z. T., Sheikh, N., Bahri, L., Soliman, A., Montresor, A. & Girdzijauskas, S. (2018). CAS2VEC: Network-Agnostic Cascade Prediction in Online Social Networks. In: : . Paper presented at 2018 FIFTH INTERNATIONAL CONFERENCE ON SOCIAL NETWORKS ANALYSIS, MANAGEMENT AND SECURITY (SNAMS) (pp. 72-79). IEEE
Open this publication in new window or tab >>CAS2VEC: Network-Agnostic Cascade Prediction in Online Social Networks
Show others...
2018 (English)Conference paper, Published paper (Refereed)
Abstract [en]

Effectively predicting whether a given post or tweet is going to become viral in online social networks is of paramount importance for several applications, such as trend and break-out forecasting. While several attempts towards this end exist, most of the current approaches rely on features extracted from the underlying network structure over which the content spreads. Recent studies have shown, however, that prediction can be effectively performed with very little structural information about the network, or even with no structural information at all. In this study we propose a novel network-agnostic approach called CAS2VEC, that models information cascades as time series and discretizes them using time slices. For the actual prediction task we have adopted a technique from the natural language processing community. The particular choice of the technique is mainly inspired by an empirical observation on the strong similarity between the distribution of discretized values occurrence in cascades and words occurrence in natural language documents. Thus, thanks to such a technique for sentence classification using convolutional neural networks, CAS2VEC can predict whether a cascade is going to become viral or not. We have performed extensive experiments on two widely used real-world datasets for cascade prediction, that demonstrate the effectiveness of our algorithm against strong baselines.

Place, publisher, year, edition, pages
IEEE, 2018
National Category
Software Engineering
Identifiers
urn:nbn:se:kth:diva-252430 (URN)10.1109/SNAMS.2018.8554730 (DOI)000466979100012 ()2-s2.0-85060045802 (Scopus ID)
Conference
2018 FIFTH INTERNATIONAL CONFERENCE ON SOCIAL NETWORKS ANALYSIS, MANAGEMENT AND SECURITY (SNAMS)
Note

QC 20190715

Available from: 2019-07-15 Created: 2019-07-15 Last updated: 2019-07-15Bibliographically approved
Kefato, Z., Sheikh, N., Bahri, L., Soliman, A., Girdzijauskas, S. & Montresor, A. (2018). CaTS: Network-Agnostic Virality Prediction Model to Aid Rumour Detection. In: : . Paper presented at International Workshop on Rumours and Deception in Social Media (RDSM 2018).
Open this publication in new window or tab >>CaTS: Network-Agnostic Virality Prediction Model to Aid Rumour Detection
Show others...
2018 (English)Conference paper, Published paper (Refereed)
National Category
Computer Systems
Identifiers
urn:nbn:se:kth:diva-239543 (URN)
Conference
International Workshop on Rumours and Deception in Social Media (RDSM 2018)
Note

QC 20181130

Available from: 2018-11-26 Created: 2018-11-26 Last updated: 2018-11-30Bibliographically approved
Soliman, A. (2018). Graph-based Analytics for Decentralized Online Social Networks. (Doctoral dissertation). KTH Royal Institute of Technology
Open this publication in new window or tab >>Graph-based Analytics for Decentralized Online Social Networks
2018 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Decentralized Online Social Networks (DOSNs) have been introduced as a privacy preserving alternative to the existing online social networks.  DOSNs remove the dependency on a centralized provider and operate as distributed information management platforms. Current efforts of providing DOSNs are mainly focused on designing the required building blocks for managing the distributed network and supporting the social services (e.g., search, content delivery, etc.). However, there is a lack of reliable techniques for enabling complex analytical services (e.g., spam detection, identity validation, etc.) that comply with the decentralization requirements of DOSNs. In particular, there is a need for decentralized data analytic techniques and machine learning (ML) algorithms that can successfully run on top of DOSNs.

 

In this thesis, we empower decentralized analytics for DOSNs through a set of novel algorithms. Our algorithms allow decentralized analytics to effectively work on top of fully decentralized topology, when the data is fully distributed and nodes have access to their local knowledge only. Furthermore, our algorithms and methods are able to extract and exploit the latent patterns in the social user interaction networks and effectively combine them with the shared content, yielding significant improvements for the complex analytic tasks. We argue that, community identification is at the core of the learning and analytical services provided for DOSNs. We show in this thesis that knowledge on community structures and information dissemination patterns, embedded in the topology of social networks has a potential to greatly enhance data analytic insights and improve results. At the heart of this thesis lies a community detection technique that successfully extracts communities in a completely decentralized manner. In particular, we show that multiple complex analytic tasks, like spam detection and identity validation,  can be successfully tackled by harvesting the information from the social network structure. This is achieved by using decentralized community detection algorithm which acts as the main building block for the community-aware learning paradigm that we lay out in this thesis. To the best of our knowledge, this thesis represents the first attempt to bring complex analytical services, which require decentralized iterative computation over distributed data, to the domain of DOSNs. The experimental evaluation of our proposed algorithms using real-world datasets confirms the ability of our solutions to generate  efficient ML models in massively parallel and highly scalable manner.

Place, publisher, year, edition, pages
KTH Royal Institute of Technology, 2018. p. 41
Series
TRITA-EECS-AVL ; 2018:4
Keywords
Decentralized Community Detection, Community-aware Learning, Spam Detection, Identity Validation
National Category
Computer Systems
Research subject
Information and Communication Technology
Identifiers
urn:nbn:se:kth:diva-222228 (URN)978-91-7729-666-9 (ISBN)
Public defence
2018-03-09, sal C, Electrum building, Kistagången 16, STOCKHOLM, 09:00 (English)
Opponent
Supervisors
Note

QC 20180205

Available from: 2018-02-05 Created: 2018-02-02 Last updated: 2018-02-05Bibliographically approved
Soliman, A., Rahimian, F. & Girdzijauskas, S. (2018). Stad: Stateful Diffusion for Linear Time Community Detection. In: 38th IEEE International Conference on Distributed Computing Systems: . Paper presented at 38th IEEE International Conference on Distributed Computing Systems, ICDCS 2018; Vienna University of Technology (TU Wien)Vienna; Austria; 2 July 2018 through 5 July 2018.
Open this publication in new window or tab >>Stad: Stateful Diffusion for Linear Time Community Detection
2018 (English)In: 38th IEEE International Conference on Distributed Computing Systems, 2018Conference paper, Published paper (Refereed)
Abstract [en]

Community detection is one of the preeminent topics in network analysis. Communities in real-world networks vary in their characteristics, such as their internal cohesion and size. Despite a large variety of methods proposed to detect communities so far, most of existing approaches fall into the category of global approaches. Specifically, these global approaches adapt their detection model focusing on approximating the global structure of the whole network, instead of performing approximation at the communities level. Global techniques tune their parameters to “one size fits all” model, so they are quite successful with extracting communities in homogeneous cases but suffer in heterogeneous community size distributions. In this paper, we present a stateful diffusion approach (Stad) for community detection that employs diffusion. Stad boosts diffusion with a conductance-based function that acts like a tuning parameter to control the diffusion speed. In contrast to existing diffusion mechanisms which operate with global and fixed speed, Stad introduces stateful diffusion to treat every community individually. Particularly, Stad controls the diffusion speed at node level, such that each node determines the diffusion speed associated with every possible community membership independently. Thus, Stad is able to extract communities more accurately in heterogeneous cases by dropping “one size fits all” model. Furthermore, Stad employs a vertex-centric approach which is fully decentralized and highly scalable, and requires no global knowledge. So as, Stad can be successfully applied in distributed environments, such as large-scale graph processing or decentralized machine learning. The results with both real-world and synthetic datasets show that Stad outperforms the state-of-the-art techniques, not only in the community size scale issue but also by achieving higher accuracy that is twice the accuracy achieved by the state-of-the-art techniques.

Keywords
Community Detection, Flow Models, Random Walks, Diffusion, Stateful Diffusion
National Category
Computer Systems
Identifiers
urn:nbn:se:kth:diva-231832 (URN)10.1109/ICDCS.2018.00107 (DOI)2-s2.0-85050963074 (Scopus ID)
Conference
38th IEEE International Conference on Distributed Computing Systems, ICDCS 2018; Vienna University of Technology (TU Wien)Vienna; Austria; 2 July 2018 through 5 July 2018
Note

QC 20180703

Available from: 2018-07-03 Created: 2018-07-03 Last updated: 2018-10-30Bibliographically approved
Soliman, A. & Girdzijauskas, S. (2017). Adagraph: Adaptive graph-based algorithms for spam detection in social networks. In: 5th International Conference on Networked Systems, NETYS 2017: . Paper presented at 17 May 2017 through 19 May 2017 (pp. 338-354). Springer Verlag
Open this publication in new window or tab >>Adagraph: Adaptive graph-based algorithms for spam detection in social networks
2017 (English)In: 5th International Conference on Networked Systems, NETYS 2017, Springer Verlag , 2017, p. 338-354Conference paper, Published paper (Refereed)
Abstract [en]

In the past years, researchers developed approaches to detect spam in Online Social Networks (OSNs) such as URL blacklisting, spam traps and even crowdsourcing for manual classification. Although previous work has shown the effectiveness of using statistical learning to detect spam, existing work employs supervised schemes that require labeled training data. In addition to the heavy training cost, it is difficult to obtain a comprehensive source of ground truth for measurement. In contrast to existing work, in this paper we present AdaGraph that is a novel graph-based approach for spam detection. AdaGraph is unsupervised, hence it diminishes the need of labeled training data and training cost. Particularly, AdaGraph effectively detects spam in large-scale OSNs by analyzing user behaviors using graph clustering technique. Moreover, AdaGraph continuously updates detected communities to comply with users dynamic interactions and activities. Extensive experiments using Twitter datasets show that AdaGraph detects spam with accuracy 92.3%. Furthermore, the false positive rate of AdaGraph is less than 0.3% that is less than half of the rate achieved by the state-of-the-art approaches.

Place, publisher, year, edition, pages
Springer Verlag, 2017
Keywords
Community detection, Distributed systems, Evolving graphs algorithms, Social networks, Unsupervised spam detection, Behavioral research, Graphic methods, Evolving graphs, Graph-based algorithms, Labeled training data, Online social networks (OSNs), Spam detection, State-of-the-art approach, Social networking (online)
National Category
Computer Systems
Identifiers
urn:nbn:se:kth:diva-216569 (URN)10.1007/978-3-319-59647-1_25 (DOI)2-s2.0-85019722417 (Scopus ID)9783319596464 (ISBN)
Conference
17 May 2017 through 19 May 2017
Note

QC 20171101

Available from: 2017-11-01 Created: 2017-11-01 Last updated: 2018-02-02Bibliographically approved
Yanggratoke, R. & El Hosary, A. (2016). Selected Paper on Network and Cloud Analytics. KTH Royal Institute of Technology
Open this publication in new window or tab >>Selected Paper on Network and Cloud Analytics
2016 (English)Report (Other academic)
Abstract [en]

This report reviews selected papers from the ones presented in the seminar on Network and Cloud Analytics since April 2015 till November 2015 (realm.sics.se). During this time period, the seminar discussed 43 papers that span different research disciplines, such as analytics for network management, network anomaly detection, large-scale machine learning, and learning under concept drift. From those papers, we select 13 papers that provide compelling contributions and possible extensions for future work. Additionally, we grouped the selected papers based on their problem area. For each selected paper, we identify the problem that the authors try to solve, major challenges that make the problem difficult, a proposed approach to solve the problem, and key contributions of the paper. Further, we show the limitations of the proposed method and suggest ideas for applying the paper to our research projects.

Place, publisher, year, edition, pages
KTH Royal Institute of Technology, 2016. p. 17
Keywords
Analytics, Machine learning
National Category
Computer Systems Communication Systems
Identifiers
urn:nbn:se:kth:diva-180061 (URN)
Projects
REALM
Funder
VINNOVA, 2013-03895
Note

Qc 20160212

Available from: 2016-01-07 Created: 2016-01-07 Last updated: 2016-02-12Bibliographically approved
Soliman, A., Bahri, L., Carminati, B., Ferrari, E. & Girdzijauskas, S. (2015). DIVa: Decentralized Identity Validation for Social Networks. KTH Royal Institute of Technology
Open this publication in new window or tab >>DIVa: Decentralized Identity Validation for Social Networks
Show others...
2015 (English)Report (Other academic)
Abstract [en]

We suggested DIVa, a decentralized, unsupervised, and association rule mining based solution for the learning of fine-grained correlations between profile attributes in Online Social Networks. These correlations can be used for identity validation purposes. In this report, we provide the technical details and the security analysis proofs of the DIVa model.

Place, publisher, year, edition, pages
KTH Royal Institute of Technology, 2015. p. 6
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:kth:diva-164397 (URN)
Projects
iSocial
Note

QC 20150417

Available from: 2015-04-16 Created: 2015-04-16 Last updated: 2015-04-17Bibliographically approved
Soliman, A., Bahri, L., Carminati, B., Ferrari, E. & Girdzijauskas, S. (2015). DIVa: Decentralized Identity Validation for Social Networks. In: PROCEEDINGS OF THE 2015 IEEE/ACM INTERNATIONAL CONFERENCE ON ADVANCES IN SOCIAL NETWORKS ANALYSIS AND MINING (ASONAM 2015): . Paper presented at IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), AUG 25-28, 2015, Paris, FRANCE (pp. 383-391). Association for Computing Machinery (ACM)
Open this publication in new window or tab >>DIVa: Decentralized Identity Validation for Social Networks
Show others...
2015 (English)In: PROCEEDINGS OF THE 2015 IEEE/ACM INTERNATIONAL CONFERENCE ON ADVANCES IN SOCIAL NETWORKS ANALYSIS AND MINING (ASONAM 2015), Association for Computing Machinery (ACM), 2015, p. 383-391Conference paper, Published paper (Refereed)
Abstract [en]

Online Social Networks exploit a lightweight process to identify their users so as to facilitate their fast adoption. However, such convenience comes at the price of making legitimate users subject to different threats created by fake accounts. Therefore, there is a crucial need to empower users with tools helping them in assigning a level of trust to whomever they interact with. To cope with this issue, in this paper we introduce a novel model, DIVa, that leverages on mining techniques to find correlations among user profile attributes. These correlations are discovered not from user population as a whole, but from individual communities, where the correlations are more pronounced. DIVa exploits a decentralized learning approach and ensures privacy preservation as each node in the OSN independently processes its local data and is required to know only its direct neighbors. Extensive experiments using real-world OSN datasets show that DIVa is able to extract fine-grained community-aware correlations among profile attributes with average improvements up to 50% than the global approach.

Place, publisher, year, edition, pages
Association for Computing Machinery (ACM), 2015
Keywords
Community-aware Identity Validation, Ensemble Learning, Privacy-preserving Learning, Decentralized Online Social Networks
National Category
Communication Studies
Identifiers
urn:nbn:se:kth:diva-185412 (URN)10.1145/2808797.2808861 (DOI)000371793500054 ()2-s2.0-84962492143 (Scopus ID)978-1-4503-3854-7 (ISBN)
Conference
IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), AUG 25-28, 2015, Paris, FRANCE
Note

QC 20160421

Available from: 2016-04-21 Created: 2016-04-18 Last updated: 2018-02-02Bibliographically approved
Soliman, A.Stad: Stateful Diffusion for Linear Time Community Detection.
Open this publication in new window or tab >>Stad: Stateful Diffusion for Linear Time Community Detection
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Community detection is one of the preeminent topics in network analysis. Communities in real-world networks vary in their characteristics, such as their internal cohesion and size. Despite a large variety of methods proposed to detect communities so far, most of existing approaches fall into the category of global approaches. Specifically, these global approaches adapt their detection model focusing on approximating the global structure of the whole network, instead of performing approximation at the communities level. Global techniques tune their parameters to "one size fits all" model, so they are quite successful with extracting communities in homogeneous cases but suffer in heterogeneous community size distributions.

In this paper, we present a stateful diffusion approach (Stad) for community detection that employs diffusion. Stad boosts diffusion with conductance-based function that acts like a tuning parameter to control the diffusion speed. In contrast to existing diffusion mechanisms which operate with global and fixed speed, Stad introduces stateful diffusion to treat every community individually. Particularly, Stad controls the diffusion speed at node level, such that each node determines the diffusion speed associated with every possible community membership independently. Thus, Stad is able to extract communities more accurately in heterogeneous cases by dropping "one size fits all" model. Furthermore, Stad employs a vertex-centric approach which is fully decentralized and highly scalable, and requires no global knowledge. So as, Stad can be successfully applied in distributed environments, such as large-scale graph processing or decentralized machine learning. The results with both real-world and synthetic datasets show that Stad outperforms the state-of-the-art techniques, not only in the community size scale issue but also by achieving higher accuracy that is twice the accuracy achieved by the state-of-the-art techniques.

National Category
Computer Systems
Identifiers
urn:nbn:se:kth:diva-222283 (URN)
Note

QC 20180205

Available from: 2018-02-05 Created: 2018-02-05 Last updated: 2018-02-05Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-0264-8762

Search in DiVA

Show all publications