Selecting Walk Schemes for Database Embedding

ACM International Conference on Information and Knowledge Management (CIKM), pp. 1677–1686

Abstract

Machinery for data analysis often requires a numeric representation of the input. Towards that, a common practice is to embed components of structured data into a high-dimensional vector space. We study the embedding of the tuples of a relational database, where existing techniques are often based on optimization tasks over a collection of random walks from the database. The focus of this paper is on the recent FoRWaRD algorithm that is designed for dynamic databases, where walks are sampled by following foreign keys between tuples. Importantly, different walks have different schemas, or ?walk schemes," that are derived by listing the relations and attributes along the walk. Also importantly, different walk schemes describe relationships of different natures in the database.

Authors 4

1. Yuval Lev Lubarsky

   Technion – Israel Institute of Technology

   Affiliation as printed

   Technion, Haifa, Israel

2. Jan Tönshof Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, Aachen, Germany

3. Martin Grohe Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, Aachen, Germany

4. Benny Kimelfeld

   Technion – Israel Institute of Technology

   Affiliation as printed

   Technion, Haifa, Israel