2013–, with M. Brambilla.
Systems and methods to process, integrate and analyse data at scale — from distributed stream processing and complex event recognition to urban data science and, more recently, the integration of data and knowledge with Large Language Models.
Where the two stream reasoning lines are about what a method can do in principle, this one is about what survives contact with real volumes and real deployments. Much of it came out of work on city data: fusing mobile telecom, social media and transport data to understand how a city behaves during a large event, which is also where the CitySensing work and the IBM Faculty Award on City Data Fusion belong.
Selected works
-
Integrating Large Language Models and Knowledge Graphs for Extraction and Validation of Textual Test Data
Antonio De Santis, Marco Balduini, Federico De Santis, Andrea Proia, Arsenio Leo, Marco Brambilla, Emanuele Della Valle
The Semantic Web – ISWC 2024 – 23rd International Semantic Web Conference, Baltimore, MD, USA, November 11-15, 2024, Proceedings, Part III, 2024Combines Large Language Models and Knowledge Graphs to extract test data from textual documents in the aerospace domain and to validate the extracted data, in collaboration with Thales Alenia Space.
-
D²IA: User-defined interval analytics on distributed streams
Ahmed Awad, Riccardo Tommasini, Samuele Langhi, Mahmoud Kamel, Emanuele Della Valle, Sherif Sakr
Inf. Syst., 2022Journal extension of D²IA that makes interval analytics run efficiently on distributed streams on top of Flink.
-
Chimera: A Bridge Between Big Data Analytics and Semantic Technologies — Best Paper Award, ISWC 2021
Matteo Belcao, Emanuele Falzone, Enea Bionda, Emanuele Della Valle
The Semantic Web – ISWC 2021 – 20th International Semantic Web Conference, ISWC 2021, Virtual Event, October 24-28, 2021, Proceedings, 2021Ontology-Based Data Access systems such as Ontop worked only on relational databases, leaving a gap with big data engines. Chimera fills it with OntopSpark and PySPARQL: data scientists can query a Spark data lake with SPARQL and save the semantic results back into the lake, enabling round-tripping data science pipelines. Best Paper Award at ISWC 2021.
-
The future is big graphs: a community view on graph processing systems
Sherif Sakr, Angela Bonifati, Hannes Voigt, Alexandru Iosup, Khaled Ammar, Renzo Angles, Walid G. Aref, Marcelo Arenas, Maciej Besta, Peter A. Boncz, Khuzaima Daudjee, Emanuele Della Valle, Stefania Dumbrava, Olaf Hartig, Bernhard Haslhofer, Tim Hegeman, Jan Hidders, Katja Hose, Adriana Iamnitchi, Vasiliki Kalavri, Hugo Kapp, Wim Martens, M. Tamer Özsu, Eric Peukert, Stefan Plantikow, Mohamed Ragab, Matei Ripeanu, Semih Salihoglu, Christian Schulz, Petra Selmer, Juan F. Sequeda, Joshua Shinavier, Gábor Szárnyas, Riccardo Tommasini, Antonino Tumeo, Alexandru Uta, Ana Lucia Varbanescu, Hsiang-Yun Wu, Nikolay Yakovets, Da Yan, Eiko Yoneki
Commun. ACM, 2021A community view, born at a Dagstuhl seminar, on the present and future of graph processing systems and the research challenges they face.
-
D²IA: Stream Analytics on User-Defined Event Intervals — Best Paper Award, CAiSE 2019
Ahmed Awad, Riccardo Tommasini, Mahmoud Kamel, Emanuele Della Valle, Sherif Sakr
Advanced Information Systems Engineering – 31st International Conference, CAiSE 2019, Rome, Italy, June 3-7, 2019, Proceedings, 2019Big stream processing engines treat events as instantaneous points, which cannot express questions such as ‘for how long did the temperature keep rising?’. D²IA introduces abstract operators to define analytics on user-defined event intervals and to reason about temporal relations between intervals and point events, implemented on Esper and Flink. Best Paper Award at CAiSE 2019.
-
Cost-Aware Streaming Data Analysis: Distributed vs Single-Thread
Marco Balduini, Sivam Pasupathipillai, Emanuele Della Valle
Proceedings of the 12th ACM International Conference on Distributed and Event-based Systems, DEBS 2018, Hamilton, New Zealand, June 25-29, 2018, 2018An empirical study of the cost of horizontal scalability: it compares two performance-equivalent solutions to a real streaming analysis task from the telecommunication industry, one on Apache Spark and one single-threaded, and shows that the distributed solution’s benefits are outweighed by the cost of distributed data ingestion, for both continuous and periodic analysis.
-
Stream Processing Languages in the Big Data Era
Martin Hirzel, Guillaume Baudart, Angela Bonifati, Emanuele Della Valle, Sherif Sakr, Akrivi Vlachou
SIGMOD Rec., 2018A survey of stream processing languages in the Big Data era, which organises the families of languages proposed by different communities and discusses their strengths, weaknesses, and open challenges.
-
Defining the execution semantics of stream processing engines
Lorenzo Affetti, Riccardo Tommasini, Alessandro Margara, Gianpaolo Cugola, Emanuele Della Valle
J. Big Data, 2017Every modern stream processing engine defines its own processing model, and no standard execution semantics has emerged. Building on the SECRET model, the paper formally analyses and compares the execution semantics of Flink, Storm, Spark Streaming, Google Dataflow, and Azure Stream Analytics.
-
CitySensing: Fusing City Data for Visual Storytelling — Best Paper Award, IEEE MultiMedia
Marco Balduini, Emanuele Della Valle, Matteo Azzi, Roberto Larcher, Fabrizio Antonelli, Paolo Ciuccarelli
IEEE Multim., 2015CitySensing fuses social media and mobile telecom data to tell, in real time and through interactive visualizations, the story of what happens in a city during large events such as the Milano Design Week. Best Paper Award of IEEE MultiMedia.