Keynote Speakers

Fabrizio Silvestri

Facebook, UK




Title:Applications of Similarity Search to Socially Relevant Problems

Abstract: The Facebook AI team in London deals with applying artificial intelligence techniques to address societal problems such as the spread of online misinformation, or the integrity of election processes around the world. To do so, we have developed throughout the last years a set of tools that exploit similarity search technologies to efficiently and effectively run a very high number of classification tasks on a massive set of data.

In this talk, we are going to review some of the problems we have studied in the last year and we are going to show some of the solutions we have adopted in order to make the system run efficiently. We are also going to showcase some details of an internal project that uses similarity search as a core operation to allow efficient and effective inference operations.

Bio: Fabrizio Silvestri is a Software Engineer at Facebook London in the Search Systems team. His interests are in web search in general and in particular his specialization is building systems to better interpret queries from search users. Prior to Facebook, Fabrizio was a principal scientist at Yahoo where he has worked on sponsored search and native ads within the Gemini project. Fabrizio holds a Ph.D. in Computer Science from the University of Pisa, Italy where he studied problems related to Web Information Retrieval with particular focus on Efficiency related problems like Caching, Collection Partitioning, and Distributed IR in general.

Divesh Srivastava

AT&T Labs-Research, USA




Title:Repairing noisy graphs

Abstract: Graphs are a flexible way to represent data in a variety of applications, with nodes representing domain-specific entities (e.g., records in record linkage, products and types in an ontology) and edges capturing a variety of relationships between these entities (e.g., an equivalence relationship between records in record linkage, a type-subtype relationship between types in an ontology). Often, the edges in this graph are inferred based on similarities between nodes and are noisy, in that some edges are missing (i.e., real-world relationships that do not have corresponding edges in the graph) and some edges are spurious (i.e., edges in the graph that do not have corresponding real-world relationships). Directly analyzing such graphs can lead to undesirable outcomes, making it important to repair noisy graphs. In this talk, we describe an approach that takes advantage of properties of real-world relationships and their estimated probabilities to ask oracle queries (an abstraction of crowdsourcing) to efficiently repair the noisy graphs. We illustrate this approach for the case of graphs that are unions of cliques (which is the case for record linkage) and graphs that are trees (which is the case for ontologies), and present theoretical and empirical results for these cases.

Bio: Divesh Srivastava is the head of Database Research at AT&T Labs-Research. He is a Fellow of the Association for Computing Machinery (ACM), the Vice President of the VLDB Endowment, and on the ACM Publications Board. His research interests and publications span a variety of topics in data management. He received his Ph.D. from the University of Wisconsin, Madison, USA, and his Bachelor of Technology from the Indian Institute of Technology, Bombay, India.

Alexander Tuzhilin
New York University