go back to the main page

 SSS Abstracts 
Spring 2017

go back to the main page

MXNet: Flexible Deep Learning Framework from Distributed GPU Clouds to Embedded Systems

Friday, February 3rd, 2017 from 12-1 pm in GHC 6501.

Presented by Mu Li, CSD

This talk will describe MXNet that is a new deep learning framework developed by collaborators from over 10 institutes. It is designed for both flexiblity and optimized performance, with easy to use interfaces in 7 programming languages including Python, Scala and R. We will discuss the technologies to scale out the framework to distributed clouds, in which we can achieve over 110x speedup by using 128 GPUs without slowing down the convergence rate, and also memory optimizations to fit into embedded systems like mobile phones.

In Partial Fulfillment of the Speaking Requirement

FLOCK: Combating Astroturfing on Livestreaming Platforms

Friday, March 24th, 2017 from 12-1 pm in GHC 6501.

Presented by Neil Shah, CSD

ivestreaming platforms have become increasingly popular in recent years as a means of sharing and advertising creative content. Popular content streamers who attract large viewership to their live broadcasts can earn a living by means of ad revenue, donations and channel subscriptions. Unfortunately, this incentivized popularity has simultaneously resulted in incentive for fraudsters to provide services to astroturf, or artificially inflate viewership metrics by providing fake live views to customers. Our work provides a number of major contributions: (a) formulation: we are the first to introduce and characterize the viewbot fraud problem in livestreaming platforms, (b) methodology: we propose FLOCK, a principled and unsupervised method which efficiently and effectively identifies botted broadcasts and their constituent botted views, and (c) practicality: our approach achieves over 98% precision in identifying botted broadcasts and over 90% precision/recall against sizable synthetically generated viewbot attacks on a real-world livestreaming workload of over 16 million views and 92 thousand broadcasts. FLOCK successfully operates on larger datasets in practice and is regularly used at a large, undisclosed livestreaming corporation.

In Partial Fulfillment of the Speaking Requirement

Web contact: sss+www@cs