Facebook

About: Facebook is a company organization based out in Tel Aviv, Israel. It is known for research contribution in the topics: Computer science & Artificial neural network. The organization has 7856 authors who have published 10906 publications receiving 570123 citations. The organization is also known as: facebook.com & FB.

Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture

Abstract: In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and semantic labeling. We use a multiscale convolutional network that is able to adapt easily to each task using only small modifications, regressing from the input image to the output map directly. Our method progressively refines predictions using a sequence of scales, and captures many image details without any superpixels or low-level segmentation. We achieve state-of-the-art performance on benchmarks for all three tasks.

Exposure to ideologically diverse news and opinion on Facebook

Abstract: Exposure to news, opinion and civic information increasingly occurs through social media. How do these online networks influence exposure to perspectives that cut across ideological lines? Using de-identified data, we examined how 10.1 million U.S. Facebook users interact with socially shared news. We directly measured ideological homophily in friend networks, and examine the extent to which heterogeneous friends could potentially expose individuals to cross-cutting content. We then quantified the extent to which individuals encounter comparatively more or less diverse content while interacting via Facebook’s algorithmically ranked News Feed, and further studied users’ choices to click through to ideologically discordant content. Compared to algorithmic ranking, individuals’ choices about what to consume had a stronger effect limiting exposure to cross-cutting content.

End-to-End Object Detection with Transformers

Abstract: We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components like a non-maximum suppression procedure or anchor generation that explicitly encode our prior knowledge about the task. The main ingredients of the new framework, called DEtection TRansformer or DETR, are a set-based global loss that forces unique predictions via bipartite matching, and a transformer encoder-decoder architecture. Given a fixed small set of learned object queries, DETR reasons about the relations of the objects and the global image context to directly output the final set of predictions in parallel. The new model is conceptually simple and does not require a specialized library, unlike many other modern detectors. DETR demonstrates accuracy and run-time performance on par with the well-established and highly-optimized Faster R-CNN baseline on the challenging COCO object detection dataset. Moreover, DETR can be easily generalized to produce panoptic segmentation in a unified manner. We show that it significantly outperforms competitive baselines. Training code and pretrained models are available at https://github.com/facebookresearch/detr.

Apache Hadoop YARN: yet another resource negotiator

Abstract: The initial design of Apache Hadoop [1] was tightly focused on running massive, MapReduce jobs to process a web crawl. For increasingly diverse companies, Hadoop has become the data and computational agora---the de facto place where data and computational resources are shared and accessed. This broad adoption and ubiquitous usage has stretched the initial design well beyond its intended target, exposing two key shortcomings: 1) tight coupling of a specific programming model with the resource management infrastructure, forcing developers to abuse the MapReduce programming model, and 2) centralized handling of jobs' control flow, which resulted in endless scalability concerns for the scheduler. In this paper, we summarize the design, development, and current state of deployment of the next generation of Hadoop's compute platform: YARN. The new architecture we introduced decouples the programming model from the resource management infrastructure, and delegates many scheduling functions (e.g., task fault-tolerance) to per-application components. We provide experimental evidence demonstrating the improvements we made, confirm improved efficiency by reporting the experience of running YARN on production environments (including 100% of Yahoo! grids), and confirm the flexibility claims by discussing the porting of several programming frameworks onto YARN viz. Dryad, Giraph, Hoya, Hadoop MapReduce, REEF, Spark, Storm, Tez.

A 61-million-person experiment in social influence and political mobilization

Abstract: Online social networks are everywhere. They must be influencing the way society is developing, but hard evidence is scarce. For instance, the relative effectiveness of online friendships and face-to-face friendships as drivers of social change is not known. In what may be the largest experiment ever conducted with human subjects, James Fowler and colleagues randomly assigned messages to 61 million Facebook users on Election Day in the United States in 2010, and tracked their behaviour both online and offline, using publicly available records. The results show that the messages influenced the political communication, information-seeking and voting behaviour of millions of people. Social messages had more impact than informational messages and 'weak ties' were much less likely than 'strong ties' to spread behaviour via the social network. Thus online mobilization works primarily through strong-tie networks that may exist offline but have an online representation.