Today we’re excited to be joined by return guest Michael Bronstein, Professor at Imperial College London, and Head of Graph Machine Learning at Twitter.
Subscribe: iTunes / Google Play / Spotify / RSS
We last spoke with Michael at NeurIPS in 2017 about Geometric Deep Learning. Since then, his research focus has slightly shifted to exploring graph neural networks. In our conversation, we discuss the evolution of the graph machine learning space, contextualizing Michael’s work on geometric deep learning and research on non-euclidian unstructured data. We also talk about his new role at Twitter and some of the research challenges he’s faced, including scalability and working with dynamic graphs. Michael also dives into his work on differential graph modules for graph CNNs, and the various applications of this work.
Connect with Michael!
Resources
- #90 – Geometric Deep Learning with Joan Bruna and Michael Bronstein
- Blog: Expressive power of graph neural networks and the Weisfeiler-Lehman test
- Paper: Temporal Graph Networks for Deep Learning on Dynamic Graphs
- Paper: Privacy-Preserving Recommender Systems Challenge on Twier’s Home Timeline
- Paper: SIGN: Scalable Inception Graph Neural Networks
- Paper: Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
- Paper: Differentiable Graph Module (DGM) for Graph Convolutional Networks
- A Deep Learning Approach to Antibiotic Discovery
- Paper: Adversarial Attacks on Neural Networks for Graph Data
- Jure Leskovec Publications
Join Forces!
- Join the TWIML Community!
- Check out our TWIML Presents: series page!
- Register for the TWIML Newsletter
- Check out the official TWIMLcon:AI Platform video packages here!
- Download our latest eBook, The Definitive Guide to AI Platforms!
“More On That Later” by Lee Rosevere licensed under CC By 4.0
Leave a Reply