publications

2024

  1. GMorph: Accelerating Multi-DNN Inference via Model Fusion
    Qizheng Yang, Tianyi Yang, Mingcan Xiang, Lijun Zhang, Haoliang Wang, Marco Serafini, and Hui Guan
    In Proceedings of the Nineteenth European Conference on Computer Systems (Eurosys), 2024
    PDF

2023

  1. GSplit: Scaling Graph Neural Network Training on Large Graphs via Split-Parallelism
    Sandeep Polisetty, Juelin Liu, Kobi Falus, Yi Ren Fung, Seung-Hwan Lim, Hui Guan, and Marco Serafini
    arXiv preprint arXiv:2303.13775, 2023
    PDF
  2. GraphMini: Accelerating Graph Pattern Matching Using Auxiliary Graphs
    Juelin Liu, Sandeep Polisetty, Hui Guan, and Marco Serafini
    In Proceedings of the 32nd International Conference on Parallel Architectures and Compilation Techniques (PACT), 2023
    PDF Repo

2022

  1. Tuning the Tail Latency of Distributed Queries Using Replication
    Nathan Ng, Hung Le, and Marco Serafini
    arXiv preprint arXiv:2212.10387, 2022
    PDF

2021

  1. Accelerating Graph Sampling for Graph Machine Learning Using GPUs
    Abhinav Jangda, Sandeep Polisetty, Arjun Guha, and Marco Serafini
    In Proceedings of the Sixteenth European Conference on Computer Systems (Eurosys), 2021
    PDF Repo
  2. Scalable Graph Neural Network Training: The Case for Sampling
    Marco Serafini, and Hui Guan
    ACM SIGOPS Operating Systems Review, 2021
    PDF
  3. Flexpushdowndb: Hybrid Pushdown and Caching in a Cloud DBMS
    Yifei Yang, Matt Youill, Matthew Woicik, Yizhou Liu, Xiangyao Yu, Marco Serafini, Ashraf Aboulnaga, and Michael Stonebraker
    Proceedings of the VLDB Endowment, 2021
    PDF

2020

  1. Livegraph: A Transactional Graph Storage System with Purely Sequential Adjacency List Scans
    Xiaowei Zhu, Guanyu Feng, Marco Serafini, Xiaosong Ma, Jiping Yu, Lei Xie, Ashraf Aboulnaga, and Wenguang Chen
    Proceedings of the VLDB Endowment, 2020
    PDF Repo
  2. Aion: Better Late than Never in Event-Time Streams
    Sergio Esteves, Gianmarco De Francisci Morales, Rodrigo Rodrigues, Marco Serafini, and Luı́s Veiga
    arXiv preprint arXiv:2003.03604, 2020
    PDF
  3. PushdownDB: Accelerating a DBMS using S3 computation
    Xiangyao Yu, Matt Youill, Matthew Woicik, Abdurrahman Ghanem, Marco Serafini, Ashraf Aboulnaga, and Michael Stonebraker
    In 2020 IEEE 36th International Conference on Data Engineering (ICDE), 2020
    PDF
  4. Do the Best Cloud Configurations Grow on Trees? An Experimental Evaluation of Black Box Algorithms for Optimizing Cloud Workloads
    Muhammad Bilal, Marco Serafini, Marco Canini, and Rodrigo Rodrigues
    Proceedings of the VLDB Endowment, 2020
    PDF

2019

  1. Choosing a Cloud DBMS: Architectures and Tradeoffs
    Junjay Tan, Thanaa Ghanem, Matthew Perron, Xiangyao Yu, Michael Stonebraker, David DeWitt, Marco Serafini, Ashraf Aboulnaga, and Tim Kraska
    Proceedings of the VLDB Endowment, 2019
    PDF
  2. Gyro: A Modular Scale-Out Layer for Single-Server DBMSs
    Habib Saissi, Marco Serafini, and Neeraj Suri
    In 2019 38th Symposium on Reliable Distributed Systems (SRDS), 2019
    PDF

2018

  1. P-store: An Elastic Database System with Predictive Provisioning
    Rebecca Taft, Nosayba El-Sayed, Marco Serafini, Yu Lu, Ashraf Aboulnaga, Michael Stonebraker, Ricardo Mayerhofer, and Francisco Andrade
    In Proceedings of the 2018 International Conference on Management of Data (SIGMOD), 2018
    PDF

2017

  1. Graph Data Mining with Arabesque
    Eslam Hussein, Abdurrahman Ghanem, Vinicius Santos Dias, Carlos HC Teixeira, Ghadeer AbuOda, Marco Serafini, Georgos Siganos, Gianmarco De Francisci Morales, Ashraf Aboulnaga, and Mohammed Zaki
    In Proceedings of the 2017 ACM International Conference on Management of Data (SIGMOD demo), 2017
    PDF
  2. Load Balancing for Skewed Streams on Heterogeneous Cluster
    Muhammad Anis Uddin Nasir, Hiroshi Horii, Marco Serafini, Nicolas Kourtellis, Rudy Raymond, Sarunas Girdzijauskas, and Takayuki Osogami
    arXiv preprint arXiv:1705.09073, 2017
    PDF
  3. Qfrag: Distributed Graph Search via Subgraph Isomorphism
    Marco Serafini, Gianmarco De Francisci Morales, and Georgos Siganos
    In Proceedings of the 2017 Symposium on Cloud Computing (SoCC), 2017
    PDF

2016

  1. When Two Choices are not Enough: Balancing at Scale in Distributed Stream Processing
    Muhammad Anis Uddin Nasir, Gianmarco De Francisci Morales, Nicolas Kourtellis, and Marco Serafini
    In 2016 IEEE 32nd International Conference on Data Engineering (ICDE), 2016
    PDF
  2. Clay: Fine-Grained Adaptive Partitioning for General Database Schemas
    Marco Serafini, Rebecca Taft, Aaron J. Elmore, Andrew Pavlo, Ashraf Aboulnaga, and Michael Stonebraker
    Proceedings of the VLDB Endowment, 2016
    PDF

2015

  1. Scalable Error Isolation for Distributed Systems
    Diogo Behrens, Marco Serafini, Flavio P Junqueira, Sergei Arnautov, and Christof Fetzer
    In 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI), 2015
    PDF
  2. The Power of Both Choices: Practical Load Balancing for Distributed Stream Processing Engines
    Muhammad Anis Uddin Nasir, Gianmarco De Francisci Morales, David Garcia-Soriano, Nicolas Kourtellis, and Marco Serafini
    In IEEE 31st International Conference on Data Engineering (ICDE), 2015
    PDF
  3. Arabesque: A System for Distributed Graph Mining
    Carlos HC Teixeira, Alexandre J Fonseca, Marco Serafini, Georgos Siganos, Mohammed J Zaki, and Ashraf Aboulnaga
    In Proceedings of the 25th Symposium on Operating Systems Principles (SOSP), 2015
    PDF Repo

2014

  1. Accordion: Elastic Scalability for Database Systems Supporting Distributed Transactions
    Marco Serafini, Essam Mansour, Ashraf Aboulnaga, Kenneth Salem, Taha Rafiq, and Umar Farooq Minhas
    Proceedings of the VLDB Endowment, 2014
    PDF
  2. E-store: Fine-Grained Elastic Partitioning for Distributed Transaction Processing Systems
    Rebecca Taft, Essam Mansour, Marco Serafini, Jennie Duggan, Aaron J Elmore, Ashraf Aboulnaga, Andrew Pavlo, and Michael Stonebraker
    Proceedings of the VLDB Endowment, 2014
    PDF

2013

  1. Piggybacking on Social Networks
    Aristides Gionis, Flavio PP Junqueira, Vincent Leroy, Marco Serafini, and Ingmar Weber
    In VLDB 2013-39th International Conference on Very Large Databases, 2013
    PDF
  2. Efficient Verification of Distributed Protocols Using Stateful Model Checking
    Habib Saissi, Péter Bokor, Can Arda Muftuoglu, Neeraj Suri, and Marco Serafini
    In Proceedings of the VLDB Endowment, 2013
    PDF
  3. On Barriers and the Gap Between Active and Passive Replication
    Flavio P Junqueira, and Marco Serafini
    In International Symposium on Distributed Computing (DISC), 2013
    PDF

2012

  1. Practical Hardening of Crash-Tolerant Systems
    Miguel Correia, Daniel Gómez Ferro, Flavio P Junqueira, and Marco Serafini
    In 2012 USENIX Annual Technical Conference (USENIX ATC), 2012
    PDF

2011

  1. To crash or not to crash: Efficient modeling of fail-stop faults
    Habib Saissi, Péter Bokor, Marco Serafini, and Neeraj Suri
    In Invited paper, Proc. of Workshop on Logical Aspects of Fault-Tolerance (LAFT, in assoc. with LICS), 2011
    PDF
  2. Leader election for replicated services using application scores
    Diogo Becker, Flavio Junqueira, and Marco Serafini
    In ACM/IFIP/USENIX 12th International Middleware Conference, 2011
    PDF
  3. Application-level diagnostic and membership protocols for generic time-triggered systems
    Marco Serafini, Péter Bokor, Neeraj Suri, Jonny Vinter, Astrit Ademaj, Wolfgang Brandstätter, Fulvio Tagliabo, and Jens Koch
    IEEE Transactions on Dependable and Secure Computing, 2011
    PDF
  4. Zab: High-Performance Broadcast for Primary-Backup Systems
    Flavio P Junqueira, Benjamin C. Reed, and Marco Serafini
    In 2011 IEEE/IFIP 41st International Conference on Dependable Systems & Networks (DSN), 2011
    PDF
  5. Efficient model checking of fault-tolerant distributed protocols
    Péter Bokor, Johannes Kinder, Marco Serafini, and Neeraj Suri
    In 2011 IEEE/IFIP 41st International Conference on Dependable Systems & Networks (DSN), 2011
    PDF
  6. Supporting domain-specific state space reductions through local partial-order reduction
    Péter Bokor, Johannes Kinder, Marco Serafini, and Neeraj Suri
    In 26th IEEE/ACM International Conference on Automated Software Engineering (ASE), 2011
    PDF

2010

  1. HP: Hybrid paxos for WANs
    Dan Dobre, Matthias Majuntke, Marco Serafini, and Neeraj Suri
    In 2010 European Dependable Computing Conference (EDCC), 2010
    PDF
  2. On efficient models for model checking message-passing distributed protocols
    Péter Bokor, Marco Serafini, and Neeraj Suri
    In International Conference on Formal Methods for Open Object-Based Distributed Systems, 2010
    PDF
  3. Scrooge: Reducing the costs of fast Byzantine replication in presence of unresponsive replicas
    Marco Serafini, Péter Bokor, Dan Dobre, Matthias Majuntke, and Neeraj Suri
    In 2010 IEEE/IFIP International Conference on Dependable Systems & Networks (DSN), 2010
    PDF
  4. Eventually linearizable shared objects
    Marco Serafini, Dan Dobre, Matthias Majuntke, Péter Bokor, and Neeraj Suri
    In Proceedings of the 29th ACM SIGACT-SIGOPS symposium on Principles of Distributed Computing (PODC), 2010
    PDF
  5. Weak consistency as a last resort
    Marco Serafini, and Flavio Junqueira
    In Proceedings of the 4th International Workshop on Large Scale Distributed Systems and Middleware (LADIS), 2010
    PDF

2009

  1. Abortable fork-linearizable storage
    Matthias Majuntke, Dan Dobre, Marco Serafini, and Neeraj Suri
    In 13th International Conference on the Principles of Distributed Systems (OPODIS), 2009
    PDF
  2. Efficient robust storage using secret tokens
    Dan Dobre, Matthias Majuntke, Marco Serafini, and Neeraj Suri
    In 11th International Symposium on Stabilization, Safety, and Security of Distributed Systems (SSS), 2009
  3. Role-based symmetry reduction of fault-tolerant distributed protocols with language support
    Péter Bokor, Marco Serafini, Neeraj Suri, and Helmut Veith
    In International Conference on Formal Engineering Methods (ICFEM), 2009
    PDF

2008

  1. Malicious Fault Characterization Exploiting Honeypot Data
    V Stankovic, E Alata, C Leita, M Serafini, O Thonnard, J Viniikka, and U Zurutuza
    In Proc. of the 7th European Dependable Computing Conference (EDCC), 2008
  2. Dependable and cost-effective architecture for X-by-wire systems with membership middleware
    K Sakurai, M Matsubara, M Serafini, and Neeraj Suri
    In Other32nd FISITA World Automotive Congress 2008, 2008
  3. Reducing the costs of large-scale BFT replication
    Marco Serafini, and Neeraj Suri
    In Proceedings of the 2nd Workshop on Large-Scale Distributed Systems and Middleware (LADIS), 2008

2007

  1. A tunable add-on diagnostic protocol for time-triggered systems
    Marco Serafini, Neeraj Suri, Jonny Vinter, Astrit Ademaj, Wolfgang Brandstatter, Fulvio Tagliabo, and Jens Koch
    In 37th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2007
    PDF
  2. The fail-heterogeneous architectural model
    Marco Serafini, and Neeraj Suri
    In 2007 26th IEEE International Symposium on Reliable Distributed Systems (SRDS), 2007
    PDF
  3. On-line diagnosis and recovery: On the choice and impact of tuning parameters
    Marco Serafini, Andrea Bondavalli, and Neeraj Suri
    IEEE Transactions on Dependable and Secure Computing, 2007
    PDF
  4. Sustaining Property Verification of Synchronous Dependable Protocols over Implementation
    Péter Bokor, Marco Serafini, Aron Sisak, András Pataricza, and Neeraj Suri
    In 10th IEEE High Assurance Systems Engineering Symposium (HASE), 2007