PODC 2023 Keynote: From Distributed Algorithms to Machine Learning and Back
Abstract: In the realm of computer science, it may seem that distributed computing and machine learning exist on opposite ends of the spectrum. However, there are many connections between the two domains, both in theory and practice. Recently, machine learning research has become excited about graphs. And when machine learning meets graphs, researchers familiar with distributed algorithms may experience a sense of déjà vu, as many classic distributed computing paradigms are being rediscovered. In my talk, I will introduce some key concepts in graph machine learning such as underreaching and oversquashing, known for decades in the distributed computing community as local and congest, respectively. Additionally, I will delve into recent breakthroughs and present intriguing open problems in this exciting intersection of fields.
Keywords: Graph neural networks; distributed computing; networks algorithms
Speaker 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.