August 21, 2017

Engineering Egress with Edge Fabric: Steering Oceans of Content to the World


Large content providers build points of presence around the world, each connected to tens or hundreds of networks. Ideally, this connectivity lets providers better serve users, but providers cannot obtain enough capacity on some preferred peering paths to handle peak traffic demands. These capacity constraints, coupled with volatile traffic and performance and the limitations of the 20 year old BGP protocol, make it difficult to best use this connectivity. This paper presents Edge Fabric, an SDN-based system we built and deployed to tackle these challenges for Facebook, which serves over two billion users from dozens of points of presence on six continents.

Brandon Schlinker, Hyojeong Kim, Timothy Cui, Ethan Katz-Bassett, Harsha V. Madhyastha, Italo Cunha, James Quinn, Saif Hasan, Petr Lapukhov, James Hongyi Zeng
August 6, 2017

Efficient Softmax Approximation for GPUs

International Conference on Machine Learning 2017

We propose an approximate strategy to efficiently train neural network based language models over very large vocabularies.

Edouard Grave, Armand Joulin, Moustapha Cisse, David Grangier, Hervé Jégou
August 3, 2017

Learning Multilingual Joint Sentence Embeddings with Neural Machine Translation

ACL workshop on Representation Learning for NLP 2017

In this paper, we use the framework of neural machine translation to learn joint sentence representations across six very different languages. Our aim is that a representation which is independent of the language, is likely to capture the underlying semantics.

Holger Schwenk, Matthijs Douze
July 31, 2017

Focal Surface Displays


We introduce focal surface displays to meet the challenge of vergence-accommodation conflict, augmenting conventional HMDs with a phase-only spatial light modulator (SLM) placed between the display screen and viewing optics. This SLM acts as a dynamic freeform lens, shaping synthesized focal surfaces to conform to the virtual scene geometry.

Nathan Matsuda, Alexander Fix, Douglas Lanman
July 30, 2017

Reading Wikipedia to Answer Open-Domain Questions

Association for Computational Linguistics (ACL 2017)

This paper proposes to tackle open- domain question answering using Wikipedia as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article.

Danqi Chen, Adam Fisch, Jason Weston, Antoine Bordes
July 30, 2017

Automatically Generating Rhythmic Verse with Neural Networks

Association for Computational Linguistics (ACL 2017)

We propose two novel methodologies for the automatic generation of rhythmic poetry in a variety of forms.

Jack Hopkins, Douwe Kiela
July 22, 2017

Densely Connected Convolutional Networks

CVPR 2017

In this paper, we embrace the observation that hat convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output, and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion.

Gao Huang, Zhuang Liu, Laurens van der Maaten, Kilian Q. Weinberger
July 21, 2017

CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning

CVPR 2017

e present a diagnostic dataset that tests a range of visual reasoning abilities. It contains minimal biases and has detailed annotations describing the kind of reasoning each question requires.

Justin Johnson, Bharath Hariharan, Laurens van der Maaten, Li Fei-Fei, Larry Zitnick, Ross Girshick
July 21, 2017

Learning Features by Watching Objects Move

CVPR 2017

This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual system, we explore whether low-level motion-based grouping cues can be used to learn an effective visual representation.

Deepak Pathak, Ross Girshick, Piotr Dollar, Trevor Darrell, Bharath Hariharan
July 21, 2017

Robocodes: Towards Generative Street Addresses from Satellite Imagery

CVPR 2017

This paper describes our automatic generative algorithm to create street addresses (Robocodes) from satellite images by learning and labeling regions, roads, and blocks. 75% of the world lacks street addresses.

Ilke Demir, Forest Hughes, Aman Raj, Kleovoulos Tsourides, Divyaa Ravichandran, Suryanarayana Murthy, Kaunil Dhruv, Sanyam Garg, Jatin Malhotra, Barrett Doo, Grace Kermani, Ramesh Raskar
July 21, 2017

Feature Pyramid Networks for Object Detection

CVPR 2017

In this paper, we exploit the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost.

Tsung-Yi Lin, Piotr Dollar, Ross Girshick, Kaiming He, Bharath Hariharan, Serge Belongie
July 21, 2017

Semantic Amodal Segmentation

CVPR 2017

Common visual recognition tasks such as classification, object detection, and semantic segmentation are rapidly reaching maturity, and given the recent rate of progress, it is not unreasonable to conjecture that techniques for many of these problems will approach human levels of performance in the next few years. In this paper we look to the future: what is the next frontier in visual recognition?

Yan Zhu, Yuandong Tian, Dimitris Mexatas, Piotr Dollar
July 21, 2017

Aggregated Residual Transformations for Deep Neural Networks

CVPR 2017

We present a simple, highly modularized network architecture for image classification.

Saining Xie, Ross Girshick, Piotr Dollar, Zhuowen Tu, Kaiming He
June 26, 2017

Enriching Word Vectors with Subword Information

Transactions of the Association for Computational Linguistics

Continuous word representations, trained on large unlabeled corpora are useful for many natural language processing tasks. Popular models that learn […]

Piotr Bojanowski, Edouard Grave, Armand Joulin, Tomas Mikolov
June 26, 2017

Multiplicative Pacing Equilibria in Auction Markets

Workshop on Algorithmic Game Theory and Data Science, ACM Conference on Economics and Computation

Budgets play a significant role in real-world sequential auction markets such as those implemented by Internet companies. To maximize the value provided to auction participants, spending is smoothed across auctions so budgets are used for the best opportunities. This paper considers a smoothing procedure that relies on pacing multipliers: for each bidder, the platform applies a factor between 0 and 1 that uniformly scales the bids across all auctions.

Vincent Conitzer, Christian Kroer, Eric Sodomka, Nicolas Stier
June 15, 2017

Formulation of Aerial Platform Environmental Requirements from Global Radiosonde Data

Journal of Unmanned Vehicle Systems

This paper demonstrates how raw observational climate data can be processed to characterize global climate histories and statistics for the formulation of aerial platform environmental requirements.

Jacob Stelman, Zhang Liu
June 8, 2017

Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

Data @ Scale

In this paper, we empirically show that on the ImageNet dataset large minibatches cause optimization difficulties, but when these are addressed the trained networks exhibit good generalization.

Priya Goyal, Piotr Dollar, Ross Girshick, Pieter Noordhuis, Lukasz Wesolowski, Aapo Kyrola, Andrew Tulloch, Yangqing Jia, Kaiming He
June 6, 2017

Analysis of Effective Impedance Transmitted to the Operator in Position-Exchange Bilateral Teleoperation

IEEE World Haptics 2017

In this paper, we analyze the impedance transmitted to the operator in bilateral teleoperation including the effects of master and slave dynamics, local and communication time delay, low-pass filtering of the velocity estimate, and controller stiffness and damping, for three different environment dynamics: free, clamped, and a mass-damper-spring.

Nick Colonnese, Allison M. Okamura
May 22, 2017

IVD: Automatic Learning and Enforcement of Authorization Rules in Online Social Networks

IEEE Symposium on Security and Privacy (IEEE S&P)

In this paper, we propose Invariant Detector (IVD), a defense-in-depth system that automatically learns authorization rules from normal data manipulation patterns and distills them into likely invariants.

Paul Marinescu, Chad Parry, Marjori Pomarole, Yuan Tian, Patrick Tague, Ioannis Papagiannis
May 6, 2017

Paradigm shift from Human Computer Interaction to Integration

Computer Human Interaction (CHI)

In 1960, JCR Licklider forecast three phases: human- computer interaction, human-computer symbiosis, and ultra-intelligent machines. Human-computer symbiosis or what we […]

Umer Farooq, Jonathan T. Grudin