Events
Past Event
WED@NICO SEMINAR: Arlei Silva, Rice University "Link Prediction with Autocovariance"
Northwestern Institute on Complex Systems (NICO)
12:00 PM
//
Lower Level, Chambers Hall
Details
Speaker:
Arlei Silva - Assistant Professor of Computer Science, Rice University
Title:
Link Prediction with Autocovariance
Abstract:
Machine learning on graphs supports various structured-data applications including social network analysis, recommender systems, and natural language processing. One could argue that link prediction is the most fundamental among the graph-related tasks. This is because link prediction not only has many concrete applications (e.g. friendship and product recommendation, uncovering protein-protein interactions) but can also be considered an (implicit or explicit) step of most graph-based machine learning pipelines due to the fact that the observed graph is often incomplete. Earlier link prediction approaches relied on expert-designed heuristics (e.g., Common Neighbors, Adamic-Adar, Preferential Attachment) to extract topological information from the network. More recently, representation learning on graphs and Graph Neural Networks (GNNs) have emerged as the predominant solutions for link prediction.
In this talk, we will introduce link prediction methods based on autocovariance, which is a multiscale random-walk-based node similarity metric. We will show that the proposed approaches achieve state-of-the-art performance on simple, signed, and attributed graphs. As some of our key findings, we show that representation learning results for node classification do not generalize to link prediction. Moreover, autocovariance is especially accurate at predicting negative links in polarized signed graphs. Finally, our results illustrate how existing approaches for training and evaluation of supervised link prediction, including those based on GNNs, picture an overly optimistic picture of their performance. We show that a simple approach combining autocovariance and attribute information outperforms several recent GNN-based link prediction methods.
Speaker Bio:
Arlei Silva is an Assistant Professor of Computer Science at Rice University. His research focuses on developing algorithms and models for mining and learning from complex datasets, broadly defined as data science, especially for data represented as graphs/networks. He is particularly interested in problems motivated by computational social science, infrastructure, and healthcare. The tools that he applies to address these problems include machine learning, network science, graph theory, linear algebra, optimization, and statistics. Professor Silva received a Ph.D in Computer Science from the University of California, Santa Barbara, advised by Ambuj Singh, where he was also a postdoctoral scholar.
Location:
In person: Chambers Hall, 600 Foster Street, Lower Level
Remote option: https://northwestern.zoom.us/j/98973037019
Passcode: NICO22
About the Speaker Series:
Wednesdays@NICO is a vibrant weekly seminar series focusing broadly on the topics of complex systems and data science. It brings together attendees ranging from graduate students to senior faculty who span all of the schools across Northwestern, from applied math to sociology to biology and every discipline in-between. Please visit: https://bit.ly/WedatNICO for information on future speakers.
Time
Wednesday, October 5, 2022 at 12:00 PM - 1:00 PM
Location
Lower Level, Chambers Hall Map
Contact
Calendar
Northwestern Institute on Complex Systems (NICO)
WED@NICO SEMINAR: Michael Dickey, NC State University "Shaping a Soft Future"
Northwestern Institute on Complex Systems (NICO)
12:00 PM
//
Lower Level, Chambers Hall
Details
Speaker:
Michael Dickey, Camille & Henry Professor, Department of Chemical and Biomolecular Engineering, NC State University
Title:
Shaping a Soft Future
Abstract:
Existing devices—such as cell phones, computers, and robots – are made from rigid materials, which is in direct contrast to the soft materials that compose the human body. In this talk, I will discuss several topics related to studying and harnessing soft materials within the context of creating devices (actuators, sensors, electronics) with tissue like properties.
· Liquid metal: Gallium-based liquid metals are often overlooked despite their remarkable properties: melting points below room temperature, water-like viscosity, low-toxicity, and effectively zero vapor pressure (they do not evaporate). Normally small volumes of liquids with large tension form spherical or hemi-spherical structures to minimize surface energy. Yet, these liquid metals can be patterned into non-spherical shapes (cones, wires, antennas) due to a thin, oxide skin that forms rapidly on its surface. Recently, we have discovered a simple way to separate the oxide from the metal as a way to deposit 2D-like oxides at ambient conditions.
· Shape reconfiguration: Perhaps the most fascinating aspect of liquid metals it the ability to use interfacial electrochemistry chemistry to remove / deposit the oxide to manipulate the surface tension of the metal over unprecedented ranges (from the largest tension of any known liquid to near zero!). This allows manipulating the shape and position of the metal for shape reconfigurable devices.
· Ionogels: Soft materials that are tough (that is, they do not readily tear or fail mechanically) are important for a number of applications, including encapsulation of devices. Recently, we discovered a simple way to create ulta-tough ionogels, which are polymer networks swollen with ionic liquids. These materials are tougher than cartilage and compatible with 3D printing.
This work has implications for soft and stretchable electronics; that is, devices with desirable mechanical properties for human-machine interfacing, soft robotics, and wearable electronics.
Speaker Bio:
Michael Dickey received a BS in Chemical Engineering from Georgia Institute of Technology (1999) and a PhD from the University of Texas (2006) under the guidance of Professor Grant Willson. From 2006-2008 he was a post-doctoral fellow in the lab of Professor George Whitesides at Harvard University. He is currently the Camille and Henry Dreyfus Professor in the Department of Chemical & Biomolecular Engineering at NC State University. He completed a sabbatical at Microsoft in 2016 and EPFL in 2023. Michael’s research interests include soft matter (liquid metals, gels, polymers) for soft and stretchable devices (electronics, energy harvesters, textiles, and soft robotics).
Location:
In person: Chambers Hall, 600 Foster Street, Lower Level
Remote option: https://northwestern.zoom.us/j/96920996561
Passcode: NICO25
About the Speaker Series:
Wednesdays@NICO is a vibrant weekly seminar series focusing broadly on the topics of complex systems, data science and network science. It brings together attendees ranging from graduate students to senior faculty who span all of the schools across Northwestern, from applied math to sociology to biology and every discipline in-between. Please visit: https://bit.ly/WedatNICO for information on future speakers.
Time
Wednesday, March 12, 2025 at 12:00 PM - 1:00 PM
Location
Lower Level, Chambers Hall Map
Contact
Calendar
Northwestern Institute on Complex Systems (NICO)
Winter Classes End
University Academic Calendar
All Day
Details
Winter Classes End
Time
Saturday, March 15, 2025
Contact
Calendar
University Academic Calendar
Spring Classes Begin - Northwestern Monday: Classes scheduled to meet on Mondays meet on this day.
University Academic Calendar
All Day
Details
Spring Classes Begin - Northwestern Monday: Classes scheduled to meet on Mondays meet on this day.
Time
Tuesday, April 1, 2025
Contact
Calendar
University Academic Calendar