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)