The course introduces students to recent advances in graph-based representation and learning, offering an overview of techniques from network science and graph machine learning. Case studies from economics, finance, and law demonstrate the practical application of these methods to real-world relational data.

01. Network science approaches to graph mining

01.01 Fundamentals of graph theory

01.02 Node-level and graph-level properties

01.03 Network motifs and community detection

01.04 Random graph models

01.05 Python tools for network analysis

01.06 Applications in law and governance

02. Machine learning methods for graph data

02.01 Node and graph embeddings

02.02 Graph neural networks

02.03 Graph generative models

02.04 Python tools for graph machine learning

02.05 Applications in finance and marketing

03. Scalable and privacy-aware network systems

03.01 Distributed systems and algorithms

03.02 Federated learning and frameworks

Machine Learning

Knowledge and Understanding: Upon completion of the course, the student will understand the fundamental concepts, recent advances, and application potential of network science methods and graph machine learning models. The student will be familiar with both theoretical principles and practical methodologies and will be able to apply these technologies to solve graph-related tasks in real-world domains.

Ability to apply knowledge and understanding: The student will be able to apply the acquired knowledge to design analytical pipelines that utilise algorithms and machine learning models for graph analysis.

Autonomy of judgment: The student will be capable of critically evaluating the outputs of graph-based analytical processes and drawing meaningful conclusions.

Communication skills: The student will be able to clearly and appropriately explain principles and methods for graph representation and learning.

Learning skills: The student will develop the ability to design and implement analytical pipelines to address graph-related tasks.

The teaching material prepared by the lecturer in addition to recommended textbooks (such as for instance slides, lecture notes, exercises, bibliography) and communications from the lecturer specific to the course can be found inside the Moodle platform › blended.uniurb.it

Teaching

Teaching is delivered remotely within the Moodle platform.

Attendance

Although strongly recommended, attendance is not mandatory.

Course books

"Graph Representation Learning" by William L. Hamilton
"Networks, Crowds, and Markets: Reasoning About a Highly Connected World" by David Easley and Jon Kleinberg
"Network Science" by Albert-László Barabási

Assessment

Assessment consists of a project whose objective will be defined in agreement with the lecturer. The student is required to submit a written report, a well-documented public repository containing the code implementation, and deliver a short presentation, followed by a discussion in which the student explains and justifies the methodological and implementation choices.

Disability and Specific Learning Disorders (SLD)

Students who have registered their disability certification or SLD certification with the Inclusion and Right to Study Office can request to use conceptual maps (for keywords) during exams.

To this end, it is necessary to send the maps, two weeks before the exam date, to the course instructor, who will verify their compliance with the university guidelines and may request modifications.

Teaching

Same as attending.

Attendance

Same as attending.

Course books

Same as attending.

Assessment

Same as attending.

Disability and Specific Learning Disorders (SLD)

Students who have registered their disability certification or SLD certification with the Inclusion and Right to Study Office can request to use conceptual maps (for keywords) during exams.

To this end, it is necessary to send the maps, two weeks before the exam date, to the course instructor, who will verify their compliance with the university guidelines and may request modifications.