Dr. Marco Serafini

Marco
Scientist
Distributed Systems
+(974) 4454 2359
Working at QCRI gives me lots of freedom and resources to pursue my research goals. Qatar is a thriving country, with an intriguing mix of modernity and tradition.

Research Focus at QCRI

At QCRI, Marco works on the scalability, dependability, and consistency of large-scale distributed systems. He is currently involved in three projects:

·         Arabesque, a system for distributed graph mining

·         Elastic database management systems (Accordion, E-Store, Clay)

·         Load balancing in distributed stream processing systems

 

For more info visit his personal homepage

Previous Experience

Prior to joining QCRI, Marco worked at Yahoo! Research in Barcelona where he studied the problem of protecting large scale distributed systems from hardware data corruption, which is becoming more and more frequent in the newest generation of CPUs. Marco also worked on the formal analysis of the Zookeeper Atomic Broadcast (Zab) protocol and introduced the notion of barrier to determine the essential difference between active replication protocols like Paxos, which exchange operations, and passive ones like Zab, which exchange state updates. Finally, he developed social piggybacking, a technique to increase the throughput of social event feed systems by identifying central users that can relay information across neighborhoods.  Marco received his PhD at TU Darmstadt. His thesis introduced the concept of Eventual Linearizability, a correctness condition for systems that are usually strongly consistent and degrade consistency only when necessary. It also introduced Scrooge, a fast Byzantine fault tolerant algorithm running on a small set of replicas.

Professional Experience

  • Yahoo! Research Barcelona (Spain), Visiting scientist, 2010-2012

Professional Associations and Awards

Professional Service:

Marco has been or will be PC member of Eurosys 2016, ICDCS 2016, ICDE 2016, SRDS 2106, IC2E 2016, SIGMOD 2016 demo, ICDCS 2015, WWW 2015, SRDS 2015, OPODIS 2014, SSS 2014, Middleware 2012 (Industry track), EDCC 2012, SOFSEM 2011

He is the co-PC chair of the PaPoC 2015 workshop (Principles and Practice of Consistency for Distributed Data), colocated with Eurosys 2015

Awards:

Nominated for the “Best PhD Thesis of 2010” by the German, Swiss and Austrian Computer Science societies and the German chapter of ACM for PhD thesis titled “Efficient and Low-Cost Fault-Tolerance for Web-Based Systems”

Education

  • PhD in computer science, TU Darmstadt (Germany), 2010

Selected Research

  • Carlos T. H. Teixeira, Alex J. Fonseca, Marco Serafini, Georgos Siganos, Mohammed J. Zaki, Ashraf Aboulnaga, "Arabesque: A System for Distributed Graph Mining". ACM Symp. on Operating Systems Principles (SOSP) 2015
  • Diogo Behrens, Marco Serafini, Sergei Arnautov, Flavio P. Junqueira, Christof Fetzer, "Scalable error isolation for distributed systems". USENIX Symp. on Networked Systems Design and Implementation (NSDI) 2015
  • Muhammad Anis Uddin Nasir, Gianmarco De Francisci Morales, David García-Soriano, Nicolas Kourtellis, Marco Serafini, "The Power of Both Choices: Practical Load Balancing for Distributed Stream Processing Engines". IEEE Int. Conf. on Data Engineering (ICDE) 2015.
  • Rebecca Taft, Essam Mansour, Marco Serafini, Jennie Duggan, Aaron J. Elmore, Ashraf Aboulnaga, Andrew Pavlo, Michael Stonebraker. "E-Store: Fine-Grained Elastic Partitioning for Distributed Transactions Processing Systems". Int. Conf. on Very Large Data Bases (VLDB) 2015
  • Marco Serafini, Essam Mansour, Ashraf Aboulnaga, Kenneth Salem, Taha Rafiq, Umar Farooq Minhas. "Accordion: Elastic Scalability for Database Systems Supporting Distributed Transactions". Int. Conf. on Very Large Data Bases (VLDB) 2014 
  • Flavio P. Junqueira and Marco Serafini.  "On Barriers and the Gap between Active and Passive Replication".  Int. Symp. on Distributed Computing (DISC) 2013.
  • Aristides Gionis, Flavio Junqueira, Vincent Leroy, Marco Serafini, Ingmar Weber, "Piggybacking on social networks", Int. Conf. on Very Large Data Bases (VLDB) 2013
  • M. Correia, D. Gómez Ferro, F. Junqueira, M. Serafini, “Practical Hardening of Crash-Tolerant Systems”, USENIX Annual Technical Conference (ATC) 2012. [video, slides]
  • F. Junqueria, B. Reed and M. Serafini, “Zab: High-Performance Broadcast for Primary-Backup Systems”, IEEE Int’l Conf. on Dependable Systems and Networks (DSN) 2011.
  • M. Serafini, D. Dobre, M. Majuntke, P. Bokor and N. Suri, “Eventually Linearizable Shared Objects”,ACM Symp on Principles of Distributed Computing (PODC), 2010.
  • Marco Serafini and Flavio Junqueira. "Weak Consistency as a Last Resort". Workshop on Large-Scale Distributed Systems and Middleware (LADIS) 2010.
  • M. Serafini, P. Bokor, D. Dobre, M. Majuntke, and N. Suri, "Scrooge: Reducing the cost of fast Byzantine replication in presence of unresponsive replicas", IEEE Int. Conf. on Dependable Systems and Networks (DSN), 2010.
Back to Top

In the Media

overweight-experiment-pic.jpg

Computer vision research aims to identify overweight people from social media face photos

16/03/2017

Researchers from MIT and the Qatar Computing Research Institute have developed a novel new facility in the current rush of interest towards computer vision – an algorithm that can identify overweight...

Read More

algorithm bridge.jpg

Algorithm can create a bridge between Clinton and Trump supporters

20/02/2017

A growing number of people have expressed their concern about high levels of polarization in society. For instance, the World Economic Forum's report on global risks lists the increasing societal ...

Read More

Yahoo Tech.JPG

The hero big data needs? Data Civilizer helps scientists conquer the clutter

29/01/2017

Big data is a big deal. With these huge data sets, analysts can gain unprecedented insight into the hidden patterns of fields like physics, healthcare, and finance. Collecting and analyzing this data...

Read More

Upcoming Events

2017

Slide1.JPG

QCRI-MIT CSAIL Annual Research Project Review 2017

Download ICS File 27/03/2017 ,

The QCRI – MIT CSAIL Annual Research Project Review is open to the public on Monday, March 27, 2017, at the HBKU Research Complex Multipurpose Room. The annual meeting is a highlight of a ...

Read More

Past Events

MLDAS 2017

(MLDAS 2017) Machine Learning and Data Analytics Symposium

Download ICS File 13/03/2017  - 14/03/2017 , Qatar National Convention Centre

Machine Learning and Data Analytics Symposium - MLDAS 2017 Building on the success of the three previous events , Boeing and QCRI will hold the Fourth Machine Learning and Data Analytics Symposium (...

Read More

ArabWic for web.jpg

Women in Data Science

Download ICS File 03/02/2017 ,

Here's a great chance to learn about the latest data science-related research in multiple domains, as part of a global project. Qatar's WiDS event will be held here at the HBKU Research Complex on ...

Read More

News Releases

EMan pic for internships (2).jpg

QCRI summer 2017 internship applications open

11/03/2017

The Qatar Computing Research Institute, part of Hamad bin Khalifa University, has announced that applications for its summer internship program have opened. The internships are being offered to ...

Read More

Patrick Winston pic (2).jpeg

Leading AI expert Patrick Winston to visit Qatar

05/03/2017

Patrick Winston, a Professor of Artificial Intelligence and Computer Science at Massachusetts Institute of Technology’s Computer Science and Artificial Intelligence Laboratory, is to visit Qatar to ...

Read More

MLDAS 2016.JPG

Boeing Partners with QCRI for fourth annual Machine Learning and Data Analytics Symposium (MLDAS)

09/02/2017

The Boeing Company has announced that it will once again partner with the Qatar Computing Research Institute (QCRI), part of Hamad bin Khalifa University, to host the fourth annual Machine Learning ...

Read More