Machine Learning for Data Streams

Albert Bifet, Professor at Telecom ParisTech, France.

Big Data and the Internet of Things (IoT) have the potential to fundamentally shift the way we interact with our surroundings. The challenge of deriving insights from the Internet of Things (IoT) has been recognized as one of the most exciting and key opportunities for both academia and industry. Advanced analysis of big data streams from sensors and devices is bound to become a key area of data mining research as the number of applications requiring such processing increases. Dealing with the evolution over time of such data streams, i.e., with concepts that drift or change completely, is one of the core issues in stream mining. In this talk, I will present an overview of data stream mining, and I will introduce some popular open source tools for data stream mining.

Bio: Albert Bifet is Professor at Telecom ParisTech, Head of  the Data, Intelligence and Graphs (DIG) Group, and Honorary Research Associate at the WEKA Machine Learning Group at University ofWaikato. Previously he worked at Huawei Noah's Ark Lab in Hong Kong, Yahoo Labs in Barcelona, University of Waikato and UPC BarcelonaTech. He is the co-author of a book on Machine Learning from Data Streams. He is one of the leaders of MOA and Apache SAMOA software environments for implementing algorithms and running experiments for online learning from evolving data streams. He was serving as Co-Chair of the Industrial track of IEEE MDM 2016, ECML PKDD 2015, and as Co-Chair of BigMine (2018-2012), and ACM SAC Data Streams Track (2019-2012)

Network monitoring in the age of "deep" network programmability

Laurent Vanbever, tenure-track assistant professor at ETH Zürich, Switzerland.

Networking as a field is on the verge of a massive paradigm shift towards "deep programmability" in which both the network control plane and the data plane are becoming fully programmable. Thanks to their ability to observe and react to traffic changes in real-time, fully programmable networks hold many promises including increased security, performance, and manageability. Yet, how to realize these promises in practice is still a widely open question. In this talk, I will share some of my views on where I see the field evolving and my experiences conducting research in "deep" programmable networks. I will focus on the topic of network monitoring and explain our quest in enabling programmable measurements; how we leverage them to extract high-quality network data; and how we can analyze and use these data to automatically drive network decisions.

Bio: Laurent Vanbever is a tenure-track assistant professor at ETH Zürich since 2015. Before that, Laurent was a Postdoctoral Research Associate at Princeton where he collaborated with Jennifer Rexford. He obtained his PhD degree in Computer Science from the University of Louvain in 2012. His research focuses on making large network infrastructures more manageable, scalable and secure. Laurent has won several awards for his research including: the SIGCOMM best paper award, the NSDI community award, and four IETF/IRTF Applied Networking Research Prizes.

Dario Rossi, Chief Expert on Network AI at Huawei Technologies, France.

Bio: Dario Rossi is Chief Expert on Network AI at Huawei Technologies, co. Ltd. He holds an HDR from UPMC (2010), as well as a PhD (2005) and MSc (2001) degrees from Politecnico di Torino. Before joining Huawei in 2018, he occupied a Chair Professor (2016-2018), Full Professor (2012-2016) and Associate Professor (2006-2012) positions at the Computer Science and Networking department of Telecom ParisTech. He was also a Professor at the LIX department of Ecole Polytechnique (2012-2018). Prior to that, he worked with the Telecommunication Network Group of the Electrical Engineering department at Politecnico di Torino (2001-2006) and held a Visiting Researcher position in the Computer Science division at University of California, Berkeley (2003-2004). He co-chaired the RT2, that federates the Institut MinesTelecom researchers working on the networking domain (about 50 people from 5 schools in France), presently serves in the Steering committees of ITC and AINTEC, chaired ACM ICN (2016), the last 2 editions of ACM SIGCOMM AINTEC (2013,2014) and of the ACM SIGCOMM PhD School on Traffic Monitoring and Analysis (2014,2018) and participated in the program committees of 50+ conferences including IEEE INFOCOM, ACM CoNEXT and ACM SIGCOMM. He is Associate Editor of IEEE Transactions on Network and Service Management and Elsevier Computer Networks, and was Associate Editor of IEEE Transactions on Green Communications and Networking and guest editor of IEEE Journal on Selected Areas in Communications. He has coauthored 8 patents and 150+ papers in leading conferences (including IEEE INFOCOM, ACM SIGCOMM, ACM CoNEXT, ACM IMC and WWW) and journals (including IEEE JSAC, ACM/IEEE TON, ACM CCR, IEEE TMM) that attracted over 5000 citations (Google scholar). His work received the Best paper award at NTMS 2012, TRAC 2014, TRAC 2015, ACM SIGCOMM Internet-QoE 2016, NOSSDAV 2018, the IEEE ComSoc/ISOC Internet Technical Committee Best Paper Award (2016-2017), the Best dataset award at PAM 2018, the Best poster award at TMA 2016, and was finalist at the IEEE INFOCOM Innovation Challenge (2016). He is Senior Member of IEEE (2013) and ACM (2015), received an IETF Applied Network Research Prize (2016), a Google Faculty Research Award (2015), and has been honored with Distinguished Member recognition from the INFOCOM TPC (2015, 2016, 2017). His current research interest include Machine learning, Internet traffic measurement, and high speed all-software networking, whereas previous interests included congestion control, Information centric networks, green networking, peer-2-peer networks, traffic engineering and vehicular networks.