Deep Learning for Graphs

Processing symbolic relationships with neural networks

Tutorial @ ECAI 2020

August, 30th 2020 h. 13.45-17.00 CET - Online

Graphs are an effective representation for complex information, providing a straightforward means to bridge numerical data and symbolic relationships. The tutorial will provide an easy paced introduction to learning for graphs, covering from foundational models to open research challenges.

Dealing with graph data requires learning models capable of adapting to structured samples of varying size and topology, capturing the relevant structural patterns to perform predictive and explorative tasks while maintaining the efficiency and scalability necessary to process large scale networks. The tutorial will first introduce foundational aspects and seminal models for learning with graph structured data. Then it will discuss the most recent advancements in terms of deep learning for network and graph data, including learning structure embeddings, graph convolutions, attentional models and graph generation.

Tutorial Outline

  • Motivations

  • Formalization of the learning task: graph prediction, induction, transduction and generation

  • Historical perspective: contractive and contextual models

  • A view on modern deep learning for graphs

o Spectral methods

o Spatial convolutions

o Node embeddings

o Unsupervised learning on graphs

  • Relevant current research challenges

o Graph pooling: global, topological and adaptive methods

o Graph generation: adjacency-based, language-based

o Expressivity and theoretical aspects

o Benchmarks and robust assessment of models

  • Applications

o Molecular graphs

o Interaction networks (life sciences, social)

o Software as a graph

o Recommendations systems

o Chemical compound generation

o Deep learning for knowledge graphs

Materials & References

Tutorial slides are available here.

For a step-by-step introduction of the topic please check on our tutorial paper:

D. Bacciu, F.Errica, A. Micheli, M. Podda, A Gentle Introduction to Deep Learning for Graphs, Neural Networks, Sept, 2020

A paper with reference results on graph classification under standardized empirical settings:

Federico Errica; Marco Podda; Davide Bacciu; Alessio Micheli, A Fair Comparison of Graph Neural Networks for Graph Classification, ICLR 2020

Check out the PyDGN library for speeding up development and validation of deep graph neural networks

Speaker Biography

Davide Bacciu - UniversitĂ  di Pisa (bacciu@di.unipi.it)

Associate Professor at the Computer Science Department, University of Pisa. The core of his research is on Machine Learning (ML) and deep learning models for structured data processing, including sequences, trees and graphs. He is the PI of an Italian National project on ML for structured data and the Coordinator of the H2020-RIA project TEACHING (2020-2022). He has been teaching courses of Artificial Intelligence (AI) and ML at undergraduate and graduate levels since 2010. He is currently supervising 13 Ph.D. students in Computer Science and Data Science, including 5 Ph.D. students whose main focus is on learning for structured data. He is an IEEE Senior Member, the founder and chair of the IEEE Task Force on learning for structured data, a member of the IEEE NN Technical Committee and of the IEEE CIS Task Force on Deep Learning. He is an Associate Editor of the IEEE Transactions on Neural Networks and Learning Systems. Since 2017 he is the Secretary of the Italian Association for Artificial Intelligence (AI*IA) and a member of CLAIRE-AI since 2018.