Learning with Graphs

Roger Wattenhofer

ETH Zurich

Abstract. Big and complex data is often represented by a graph. Graphs play an important role in various fields: in natural sciences graphs are used to represent molecules, proteins, or genomes. In math, graphs represent algebraic groups or knots. Graphs are also widely used to model social networks or traffic, and they have dozens of applications in computer science. In this talk we will discuss how machine learning can deal with graphs. While deep learning has been successfully dealing with tables, graphs are much more challenging because the input is not fixed, and extrapolation is necessary. In the talk, we will discuss a few breakthrough stories, but also some open challenges and open problems when it comes to learning with graphs.

Biography. Roger Wattenhofer is a full professor at the Information Technology and Electrical Engineering Department, ETH Zurich, Switzer­land. He received his doctorate in Computer Science from ETH Zurich. He also worked multiple years at Microsoft Research in Redmond, Washington, at Brown University in Providence, Rhode Island, and at Macquarie University in Sydney, Australia. Roger Wattenhofer’s research interests include a variety of algorithmic and systems aspects in computer science and information technology, e.g., distributed systems, positioning systems, wireless networks, mobile systems, social networks, financial networks, deep neural networks. He publishes in different communities: distributed computing (e.g., PODC, SPAA, DISC), networking and systems (e.g., SIGCOMM, SenSys, IPSN, OSDI, MobiCom), algorithmic theory (e.g., STOC, FOCS, SODA, ICALP), and more recently also machine learning (e.g., ICML, NeurIPS, ICLR, ACL, AAAI). His work received multiple awards, e.g. the Prize for Innovation in Distributed Computing for his work in Distributed Approximation. He published the book “Blockchain Science: Distributed Ledger Technology“, which has been translated to Chinese, Korean and Vietnamese.#