April 24, 2017

Tracking the World State with Recurrent Entity Networks

International Conference on Learning Representations (ICLR) 2017

We introduce a new model, the Recurrent Entity Network (EntNet). It is equipped with a dynamic long-term memory which allows it to maintain and update a representation of the state of the world as it receives new data.

Mikael Henaff, Jason Weston, Arthur Szlam, Antoine Bordes, Yann LeCun
April 24, 2017

Multi-Agent Cooperation and the Emergence of (Natural) Language

International Conference on Learning Representations (ICLR) 2017

This paper proposes a framework for language learning that relies on multi-agent communication.

Angeliki Lazaridou, Alexander Peysakhovich, Marco Baroni
April 19, 2017

Joint User-Entity Representation Learning for Event Recommendation in Social Network

2017 IEEE 33rd International Conference on Data Engineering (ICDE)

In this work, we consider the heavy sparseness in both user and event feedback history caused by short lifespans (transiency) of events and user participation patterns in a production event system. We propose to solve the resulting cold-start problems by introducing a joint representation model to project users and events into the same latent space.

Lijun Tang, Eric Yi Liu
April 3, 2017

Bag of Tricks for Efficient Text Classification

European Chapter of the Association for Computational Linguistics (EACL)

This paper explores a simple and efficient baseline for text classification.

Armand Joulin, Edouard Grave, Piotr Bojanowski, Tomas Mikolov
April 3, 2017

Detecting Large Reshare Cascades in Social Networks

International Conference on World Wide Web

In this paper, we propose SansNet, a network agnostic approach towards detecting large reshare cascades in online social networks.

Karthik Subbian, B. Aditya Prakash, Lada Adamic
April 3, 2017

Understanding Short-term Changes in Online Activity Sessions

World Wide Web (WWW)

Using data from the online social networking site Facebook, we uncover temporal patterns at a much smaller time scale: within individual sessions.

Farshad Kooti, Karthik Subbian, Winter Mason, Lada Adamic, Kristina Lerman
April 1, 2017

Spinner: Scalable Graph Partitioning in the Cloud

IEEE International Conference on Data Engineering (ICDE)

In this paper, we present a graph partitioning algorithm to partition graphs with trillions of edges.

Claudio Martella, Dionysios Logothetis, Andreas Loukas, Georgos Siganos
March 2, 2017

On User and Traffic Distribution for Extreme Rural Scenario

Radio Access Network, November 2016

In this contribution, we leverage new research results and data [5] – population density data – that provide a high-resolution view into global population density distributions.

Ali Yazdan Panah
February 25, 2017

BARCHAN: Blob Alignment for Robust CHromatographic ANalysis

Journal of Chromatography A

In this study, we present a chromatogram and template alignment method based on peak registration called BARCHAN.

Camille Couprie, Laurent Duval, Maxime Moreaud, Melinda Tebib, Sophie Henon, Vincent Souchon
February 22, 2017

Automatic Alt-text: Computer-generated Image Descriptions for Blind Users on a Social Network Service

CSCW

This paper covers the design and deployment of an automatic alt-text (AAT), a system that applies computer vision technology to identify faces, objects, and themes from photos to generate photo alt-text for screen reader users on Facebook.

Jeffrey Wieland, Julie Schiller, Omid Farivar, Shaomei Wu
February 21, 2017

Discussion Quality Diffuses in the Digital Public Square

WWW 2017

We present the results of a study on large public Facebook pages where we randomly used two different methods—most recent and social feedback—to order comments on posts.

George Berry, Sean Taylor
February 20, 2017

Knowledge transfer in SVM and neural networks

Ann Math Artif Intell

The paper considers general machine learning models, where knowledge transfer is positioned as the main method to improve their convergence properties.

Vladimir Vapnik, Rauf Izmailov
February 7, 2017

Exploring Normalization in Deep Residual Networks with Concatenated Rectified Linear Units

AAAI-17

This paper analyzes the role of Batch Normalization (BatchNorm) layers on ResNets in the hope of improving the current architecture and better incorporating other normalization techniques, such as Normalization Propagation (NormProp), into ResNets.

Wenling Shang, Justin Chiu, Kihyuk Sohn
February 4, 2017

Optimizing Function Placement for Large-Scale Data-Center Applications

International Symposium on Code Generation and Optimization (CGO)

We study the impact of function placement in the context of a simple tool we created that uses sample-based profiling data.

Guilherme Ottoni, Bertrand Maher
February 1, 2017

Optimal User Loading in Massive MIMO Systems With Regularized Zero Forcing Precoding

IEEE Wireless Communications Letters

We consider a downlink massive multiple-input multiple output system employing regularized zero-forcing precoding. We derive the asymptotic signal-to-leakage-plus-noise ratio (SLNR) as both the number of antennas and the number of users go to infinity at a fixed ratio.

Sungwoo Park, Jeonghun Park, Ali Yazdan Panah, Robert W. Heath Jr
February 1, 2017

Optimal User Loading in Massive MIMO Systems with Regularized Zero Forcing Precoding

IEEE Wireless Communications Letters

We consider a downlink massive multiple-input multiple output system employing regularized zero-forcing precoding. We derive the asymptotic signal-to-leakage-plus-noise ratio (SLNR) as both the number of antennas and the number of users go to infinity at a fixed ratio.

Sungwoo Park, Jeonghun Park, Ali Yazdan Panah, Robert W. Heath Jr
January 28, 2017

A Prototype Coarse Pointing Assembly for Laser Communication

SPIE Photonics West 2017

In this paper, we describe a coarse pointing mechanism that has been designed with an emphasis on simplicity, making use of conventional materials and commercial off-the-shelf components wherever possible.

Eric D. Miller, Michael DeSpenza, Ilya Gavrilyuk, Graham Nelson, Brent Erickson, Britney Edwards, Ethan Davis, Tony Truscott
January 8, 2017

Optimizing Space Amplification in RocksDB

CIDR 2017

RocksDB is an embedded, high-performance, persistent key-value storage engine developed at Facebook.

Siying Dong, Mark Callaghan, Leonidas Galanis, Dhruba Borthakur, Tony Savor, Michael Stumm
December 16, 2016

The Paradox of Weak Ties in 55 Countries

Journal of Economic Behavior & Organization

This is the first paper to use a single dataset and methodology to compare the importance of weak ties across countries.

Laura K. Gee, Jason J. Jones, Christopher J. Fariss, Moira Burke, James H. Fowler
December 13, 2016

Using Facebook Public Posts to Enhance Trending News Summarization

Coling

In this paper we explore using relevant Facebook public posts in addition to the news articles to improve summarization of trending news.

Chen Li, Zhongyu Wei, Yang Liu, Yang Jin, Fei Huang
Academic Programs