Events for the 2nd week of March
-
Spring 2020 Joint CSC@USC/CommNetS-MHI Seminar Series
Mon, Mar 09, 2020 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Bruno Ribeiro, Purdue University
Talk Title: Unearthing the relationship between graph neural networks and matrix factorization
Abstract: Graph tasks are ubiquitous, with applications ranging from recommendation systems, to language understanding, to automation with environmental awareness and molecular synthesis. A fundamental challenge in applying machine learning to these tasks has been encoding (representing) the graph structure in a way that ML models can easily exploit the relational information in the graph, including node and edge features. Until recently, this encoding has been performed by factor models (a.k.a. matrix factorization embeddings), which arguably originated in 1904 with Spearman's common factors. Recently, however, graph neural networks have introduced a new powerful way to encode graphs for machine learning models. In my talk, I will describe these two approaches and then introduce a unifying mathematical framework using group theory and causality that connects them. Using this novel framework, I will introduce new practical guidelines to generating and using node embeddings and graph representations, which fixes significant shortcomings of the standard operating procedures used today.
Biography: Bruno Ribeiro is an Assistant Professor in the Department of Computer Science at Purdue University. He obtained his Ph.D. at the University of Massachusetts Amherst and did his postdoctoral studies at Carnegie Mellon University from 2013-2015. His research interests are in representation learning and data mining, with a focus on sampling and modeling relational and temporal data. He received an NSF CAREER award in 2020 and the ACM SIGMETRICS best paper award in 2016.
Host: Prof. Antonio Ortega, aortega@usc.edu
More Info: http://csc.usc.edu/seminars/2020Spring/ribeiro.html
More Information: 200309_Bruno Ribeiro_CSC Seminar.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Brienne Moore
Event Link: http://csc.usc.edu/seminars/2020Spring/ribeiro.html
-
ECE Seminar: Software-Hardware Systems for the Internet of Things
Tue, Mar 10, 2020 @ 10:45 AM - 11:45 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Professor Omid Abari, School of Computer Science, University of Waterloo
Talk Title: Software-Hardware Systems for the Internet of Things
Abstract: Recently, there has been a huge interest in Internet of Things (IoT) systems, which bring the digital world into the physical world around us. However, barriers still remain to realizing the dream applications of IoT. One of the biggest challenges in building IoT systems is the huge diversity of their demands and constraints (size, energy, latency, throughput, etc.). For example, virtual reality and gaming applications require multiple gigabits-per-second throughput and millisecond latency. Tiny sensors spread around a greenhouse or smart home must be low-cost and batteryless to be sustainable in the long run. Today's networking technologies fall short in supporting these IoT applications with a hugely diverse set of constraints and demands. As such, they require distinct innovative solutions. In this talk, I will describe how we can design a new class of networking technologies for IoT by designing software and hardware jointly, with an understanding of the intended application. In particular, I will present two examples of our solutions. The first solution tackles the throughput limitations of existing IoT networks by developing new millimeter wave devices and protocols, enabling many new IoT applications, such as untethered high-quality virtual reality. The second solution tackles the energy limitations of IoT networks by introducing new wireless devices that can sense and communicate without requiring any batteries. I demonstrate how our solution is applicable in multiple, diverse domains such as HCI, medical, and agriculture. I will conclude the talk with future directions in IoT research, both in terms of technologies and applications.
Biography: Omid Abari is an Assistant Professor at the University of Waterloo, School of Computer Science. He received his Ph.D. in Electrical Engineering and Computer Science from the Massachusetts Institute of Technology (MIT) in 2018. His research interests are in the area of computer networks and mobile systems, with applications to the Internet of Things (IoT). He is currently leading the Intelligent Connectivity (ICON) Lab, where his team focuses on the design and implementation of novel software-hardware systems that deliver ubiquitous sensing, communication and computing at scale. His work has been selected for GetMobile research highlights (2018, 2019), and been featured by several media outlets, including Wired, TechCrunch, Engadget, IEEE Spectrum, and ACM Tech News.
Host: Professor Konstantinos Psounis
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Mayumi Thrasher
-
Microwave Inverse Imaging Meets Deep Learning
Tue, Mar 10, 2020 @ 11:00 AM - 12:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Uday Khankhoje, Electrical Engineering at the Indian Institute of Technology Madras
Talk Title: Microwave Inverse Imaging Meets Deep Learning
Abstract: In this talk, I will start by motivating the area of inverse microwave imaging -- an area that brings together electromagnetics, signal processing, and data analytics. The objective here is to infer the electrical properties of an object by studying how it scatters electromagnetic fields -- all without making contact, i.e. remotely. The applications are diverse, from breast cancer imaging to microwave remote sensing. At the heart of this problem lies a challenging ill-posed nonlinear optimization problem. I will describe some of the contemporary methods of solving this problem and highlight the challenges faced. Subsequently, I will present some of our recent methods and results, where we have significantly pushed the state of the art by incorporating deep neural networks into existing physics-based algorithms.
Biography: Uday Khankhoje is an Assistant Professor of Electrical Engineering at the Indian Institute of Technology Madras, Chennai, India, since 2016. He received a B.Tech. degree from the Indian Institute of Technology Bombay, Mumbai, India, in 2005, an M.S. and PhD. degrees from the California Institute of Technology (Caltech), Pasadena, USA, in 2010, all in Electrical Engineering. He was a Caltech Postdoctoral Scholar at the Jet Propulsion Laboratory (NASA/Caltech) from 2011-2012, a Postdoctoral Research Associate in the Department of Electrical Engineering at the University of Southern California, Los Angeles, USA, from 2012-2013, and an Assistant Professor of Electrical Engineering at the Indian Institute of Technology Delhi from 2013-2016. His research interests are in the area of computational electromagnetics and its applications to remote sensing and inverse imaging.
Host: Prof. Constantine Sideris, csideris@usc.edu
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Talyia White
-
ECE Seminar: Compiler and Runtime Systems for Homomorphic Encryption and Graph Analytics
Wed, Mar 11, 2020 @ 10:45 AM - 11:45 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Roshan Dathathri, PhD candidate, Dept of CS, University of Texas at Austin
Talk Title: Compiler and Runtime Systems for Homomorphic Encryption and Graph Analytics
Abstract: Distributed and heterogeneous architectures are tedious to program because devices such as CPUs, GPUs, FPGAs, and TPUs provide different programming abstractions and may have disjoint memories, even if they are on the same machine. In this talk, I present compiler and runtime systems that make it easier to develop efficient programs for privacy-preserving computation and graph analytics applications on such architectures.
Fully Homomorphic Encryption (FHE) refers to a set of encryption schemes that allow computations on encrypted data without requiring a secret key. Recent cryptographic advances have pushed FHE into the realm of practical applications. However, programming these applications remains a huge challenge, as it requires cryptographic domain expertise to ensure correctness, security, and performance. I present CHET, a domain-specific optimizing compiler, that is designed to make the task of programming neural network inference applications using FHE easier. CHET automates many laborious and error prone programming tasks including encryption parameter selection to guarantee security and accuracy of the computation, determining efficient data layouts, and performing scheme-specific optimizations. Our evaluation of CHET on a collection of popular neural networks shows that CHET-generated programs outperform expert-tuned ones by an order of magnitude.
Applications in several areas like machine learning, bioinformatics, and security need to process and analyze very large graphs. Distributed clusters are essential in processing such graphs in reasonable time. I present a novel approach to building distributed graph analytics systems that exploits heterogeneity in processor types, partitioning policies, and programming models. The key to this approach is Gluon, a domain-specific communication-optimizing substrate. Programmers write applications in a shared-memory programming system of their choice and interface these applications with Gluon using a lightweight API. Gluon enables these programs to run on heterogeneous clusters and optimizes communication in a novel way by exploiting structural and temporal invariants of graph partitioning policies. Systems built using Gluon outperform previous state-of-the-art systems and scale well up to 256 CPUs and 64 GPUs.
Biography: Roshan is a Ph.D. candidate advised by Prof. Keshav Pingali in the University of Texas at Austin. He works on domain-specific programming languages, compilers, and runtime systems that make it easy to develop efficient sparse computation and privacy-preserving computation on large-scale distributed clusters, while utilizing heterogeneous architectures. He has built programming systems for distributed and heterogeneous graph analytics and privacy-preserving neural network inferencing. He received his masters from Indian Institute of Science advised by Prof. Uday Bondhugula, where he worked on automatic parallelization of affine loop nests for distributed and heterogeneous architectures.
Host: Professor Massoud Pedram
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Mayumi Thrasher