597 Results
December 11, 2018
The Costs of Overambitious Seeding of Social Products
International Conference on Complex Networks and their Applications
Product-adoption scenarios are often theoretically modeled as “influence-maximization” (IM) problems, where people influence one another to adopt and the goal is to find a limited set of people to “seed” so as to maximize long-term adoption. In many IM models, if there is no budgetary limit on seeding, the optimal approach involves seeding everybody immediately. Here, we argue that this approach can lead to suboptimal outcomes for “social products” that allow people to communicate with one another.
By: Shankar Iyer, Lada Adamic
Data Science
Facebook AI Research December 3, 2018
Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes
Conference on Neural Information Processing Systems (NIPS)
While designing the state space of an MDP, it is common to include states that are transient or not reachable by any policy (e.g., in mountain car, the product space of speed and position contains configurations that are not physically reachable). This results in weakly-communicating or multi-chain MDPs. In this paper, we introduce TUCRL, the first algorithm able to perform efficient exploration-exploitation in any finite Markov Decision Process (MDP) without requiring any form of prior knowledge.
By: Ronan Fruit, Matteo Pirotta, Alessandro Lazaric
Facebook AI Research December 2, 2018
One-Shot Unsupervised Cross Domain Translation
Conference on Neural Information Processing Systems (NIPS)
Given a single image x from domain A and a set of images from domain B, our task is to generate the analogous of x in B. We argue that this task could be a key AI capability that underlines the ability of cognitive agents to act in the world and present empirical evidence that the existing unsupervised domain translation methods fail on this task.
By: Sagie Benaim, Lior WolfNovember 27, 2018
AnoGen: Deep Anomaly Generator
Outlier Detection De-constructed (ODD) Workshop
Motivated by the continued success of Variational Auto-Encoders (VAE) and Generative Adversarial Networks (GANs) to produce realistic-looking data we provide a platform to generate a realistic time-series with anomalies called AnoGen.
By: Nikolay LaptevNovember 27, 2018
Deep Incremental Learning for Efficient High-Fidelity Face Tracking
ACM SIGGRAPH ASIA 2018
In this paper, we present an incremental learning framework for efficient and accurate facial performance tracking. Our approach is to alternate the modeling step, which takes tracked meshes and texture maps to train our deep learning-based statistical model, and the tracking step, which takes predictions of geometry and texture our model infers from measured images and optimize the predicted geometry by minimizing image, geometry and facial landmark errors.
By: Chenglei Wu, Takaaki Shiratori, Yaser Sheikh
Computer Vision
Machine Learning November 3, 2018
The Effect of Computer-Generated Descriptions on Photo-Sharing Experiences of People with Visual Impairments
Conference on Computer-Supported Cooperative Work and Social Computing (CSCW)
Like sighted people, visually impaired people want to share photographs on social networking services, but find it difficult to identify and select photos from their albums. We aimed to address this problem by incorporating state-of-the-art computer-generated descriptions into Facebook’s photo-sharing feature.
By: Yuhang Zhao, Shaomei Wu, Lindsay Reynolds, Shiri Azenkot
Human Computer Interaction & UX November 3, 2018
How Social Ties Influence Hurricane Evacuation Behavior
Conference on Computer-Supported Cooperative Work and Social Computing (CSCW)
This work is the first of its kind, examining these phenomena across three major disasters in the United States—Hurricane Harvey, Hurricane Irma, and Hurricane Maria—using aggregated, de-identified data from over 1.5 million Facebook users.
By: Danaë Metaxa-Kakavouli, Paige Maas, Daniel P. Aldrich
Data Science November 3, 2018
RacerD: Compositional Static Race Detection
Conference on Object-Oriented Programming, Systems, Languages & Applications (OOPSLA)
Automatic static detection of data races is one of the most basic problems in reasoning about concurrency. We present RacerD—a static program analysis for detecting data races in Java programs which is fast, can scale to large code, and has proven effective in an industrial software engineering scenario.
By: Sam Blackshear, Nikos Gorogiannis, Peter O'Hearn, Ilya Sergey
Systems & Networking November 2, 2018
Do explanations make VQA models more predictable to a human?
Empirical Methods in Natural Language Processing (EMNLP)
A rich line of research attempts to make deep neural networks more transparent by generating human-interpretable ‘explanations’ of their decision process, especially for interactive tasks like Visual Question Answering (VQA). In this work, we analyze if existing explanations indeed make a VQA model – its responses as well as failures – more predictable to a human.
By: Arjun Chandrasekaran, Viraj Prabhu, Deshraj Yadav, Prithvijit Chattopadhyay, Devi Parikh
Natural Language Processing & Speech November 2, 2018
Jump to better conclusions: SCAN both left and right
Empirical Methods in Natural Language Processing (EMNLP)
Lake and Baroni (2018) recently introduced the SCAN data set, which consists of simple commands paired with action sequences and is intended to test the strong generalization abilities of recurrent sequence-to-sequence models. Their initial experiments suggested that such models may fail because they lack the ability to extract systematic rules. Here, we take a closer look at SCAN and show that it does not always capture the kind of generalization that it was designed for.
By: Joost Bastings, Marco Baroni, Jason Weston, Kyunghyun Cho, Douwe Kiela