Machine Learning and Networks - Challenges, Solutions and Tradeoffs
Anura Jayasumana
Professor, Electrical & Computer Engineering
Colorado State University
We consider the intersection of networks and machine learning in two contexts. In the first,
the data of interest for ML is in the form of a large, complex network. Here, Graph Neural
Networks (GNNs) utilize message passing for neighborhood aggregation to capture graph
topology, while Graph Embedding based Neural Networks (GENNs) distill essential graph
information into a concise representation suitable for traditional neural architectures. The
second is when the training and/or the evaluation phase of ML must be carried out over a
distributed environment such as an IoT network. These environments pose challenges due to
limited storage, communication and power, complicating the deployment of complex ML
models and impeding real-time decision-making. Our innovations in graph-coordinate based
strategies, TCNN and DVCNN, help sidestep the computational challenges faced by competing
algorithms. Experimental results, benchmarked against the Open Graph Benchmark
Leaderboard, demonstrate that TCNN and DVCNN require orders of magnitude fewer
parameters than any neural network method currently listed in the OGBN Leaderboard for both
OGBN Proteins and OGBN-Products datasets.
Date and Time
Location
Hosts
Registration
- Date: 20 Jun 2024
- Time: 06:00 PM to 08:00 PM
- All times are (UTC-06:00) Mountain Time (US & Canada)
-
Add Event to Calendar
- 400 Isotope Drive
- Colorado State University
- Fort Collins, Colorado
- United States 80521
- Building: Engineering
- Room Number: C120
- Starts 08 June 2024 12:00 AM
- Ends 20 June 2024 12:00 AM
- All times are (UTC-06:00) Mountain Time (US & Canada)
- No Admission Charge
Speakers
Anura
Machine Learning and Networks - Challenges, Solutions and Tradeoffs
See abstract
Biography:
Anura P. Jayasumana is a Professor in Electrical & Computer Engineering at
Colorado State University where he holds a joint appointment in Computer
Science. He is the Director of the Information Science and Technology Center
(ISTeC) at CSU, a university wide organization for promoting research, teaching
and service in information sciences and technologies. He received a Ph.D. and
M.S. in Electrical Engineering from Michigan State University and B.Sc. in
Electronic and Telecommunications Engineering with First Class Honors from
University of Moratuwa, Sri Lanka. His current research interests include mining
knowledge networks for radicalization detection, Internet of Things, machine
learning techniques for graphs, and synthetic data generation for machine
learning.. His research has been funded by DARPA, NSF, DoJ/NIJ, and industry.
He served as a Distinguished Lecturer of the IEEE Communications Society
(2014-17), and is currently an ACM Distinguished Speaker. He has served
extensively as a consultant to companies ranging from startups to Fortune 100.
Agenda
6:00 pm Doors Open
6:30 pm Online Broadcast starts
6:45 pm Main Presentation
8:00 End