Springer Representation Learning: Propositionalization and Embeddings

This monograph addresses advances in representation learning, a cutting-edge research area of machine learning. Representation learning refers to modern data transformation techniques that convert data of different modalities and complexity, including texts, graphs, and relations, into compact tabular representations, which effectively capture their semantic properties and relations. The monograph focuses on (i) propositionalization approaches, established in relational learning and inductive logic programming, and (ii) embedding approaches, which have gained popularity with recent advances in deep learning. The authors establish a unifying perspective on representation learning techniques developed in these various areas of modern data science, enabling the reader to understand the common underlying principles and to gain insight using selected examples and sample Python code. The monograph should be of interest to a wide audience, ranging from data scientists, machine learning researchers and students to developers, software engineers and industrial researchers interested in hands-on AI solutions. From the Back Cover This monograph addresses advances in representation learning, a cutting-edge research area of machine learning. Representation learning refers to modern data transformation techniques that convert data of different modalities and complexity, including texts, graphs, and relations, into compact tabular representations, which effectively capture their semantic properties and relations. The monograph focuses on (i) propositionalization approaches, established in relational learning and inductive logic programming, and (ii) embedding approaches, which have gained popularity with recent advances in deep learning. The authors establish a unifying perspective on representation learning techniques developed in these various areas of modern data science, enabling the reader to understand the common underlying principles and to gain insight using selected examples and sample Python code. The monograph should be of interest to a wide audience, ranging from data scientists, machine learning researchers and students to developers, software engineers and industrial researchers interested in hands-on AI solutions. About the Author Prof. Nada Lavrač (Jožef Stefan Institute, Slovenia) is Senior researcher at the Department of Knowledge Technologies at JSI (was Head of Department in 2014-2020), and Full Professor at University of Nova Gorica and International Postgraduate School Jožef Stefan (was Vice-Dean in 2016-2020). Her research interests are machine learning, data mining, text mining, knowledge management and computational creativity. She was chair of several conferences ICCC 2014, ILP 2012, AIME 2011, ..., co-chair of conferences including SOKD 2008-2010, ILP 2008, IDA 2007, DS 2006, ..., keynote speaker at KI2020, ADBIS2019, ISWC 2017, LPNMR 2015, JSMI 2014, … She is/was member of editorial boards of Artificial Intelligence in Medicine, AI Communications, New Generation Computing, Applied AI, Machine Learning Journal and Data Mining and Knowledge Discovery. She is ECCAI/EurAI Fellow, was vice-president of ECCAI (1996-98), and served as member of the International Machine Learning Society board and Artificial Intelligence in Medicine board. Vid Podpečan, PhD, is a research associate at the Department of Knowledge Technologies at the Jožef Stefan Institute. He obtained his BSc in computer science from the University of Ljubljana in 2007, and his PhD from the Jožef Stefan International Postgraduate School in 2013. His research interests include machine learning, computational systems biology, text mining and natural language processing, and robotics. He co-authored a scientific monograph and published the results of his research in more than 50 scientific publications. He is also actively involved in promoting STEAM with a focus on robotics, programming, and art for which