Institution
Company•Tel Aviv, Israel•
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.
Topics: Computer science, Artificial neural network, Language model, Context (language use), Reinforcement learning
Papers published on a yearly basis
Papers
More filters
••
24 Sep 2017
TL;DR: This paper presents PARIS, a data-driven system that uses a novel hybrid offline and online data collection and modeling framework to provide accurate performance estimates with minimal data collection, and reduces runtime prediction error by a factor of 4 for some workloads on both AWS and Azure.
Abstract: Users of cloud services are presented with a bewildering choice of VM types and the choice of VM can have significant implications on performance and cost. In this paper we address the fundamental problem of accurately and economically choosing the best VM for a given workload and user goals. To address the problem of optimal VM selection, we present PARIS, a data-driven system that uses a novel hybrid offline and online data collection and modeling framework to provide accurate performance estimates with minimal data collection. PARIS is able to predict workload performance for different user-specified metrics, and resulting costs for a wide range of VM types and workloads across multiple cloud providers. When compared to sophisticated baselines, including collaborative filtering and a linear interpolation model using measured workload performance on two VM types, PARIS produces significantly better estimates of performance. For instance, it reduces runtime prediction error by a factor of 4 for some workloads on both AWS and Azure. The increased accuracy translates into a 45% reduction in user cost while maintaining performance.
156 citations
•
06 Aug 2017TL;DR: In this article, the authors propose to fix a set of target representations, called Noise As Targets (NAT), and constrain the deep features to align to them to avoid trivial solutions and collapsing of features.
Abstract: Convolutional neural networks provide visual features that perform well in many computer vision applications. However, training these networks requires large amounts of supervision; this paper introduces a generic framework to train such networks, end-to-end, with no supervision. We propose to fix a set of target representations, called Noise As Targets (NAT), and to constrain the deep features to align to them. This domain agnostic approach avoids the standard unsupervised learning issues of trivial solutions and collapsing of features. Thanks to a stochastic batch reassignment strategy and a separable square loss function, it scales to millions of images. The proposed approach produces representations that perform on par with state-of-the-art unsupervised methods on ImageNet and PASCAL VOC.
155 citations
••
TL;DR: In this article, the authors compared the similarities and differences in their respective experiences of building and using knowledge graphs, and discussed the challenges that all knowledge-driven enterprises face today, covering the breadth of applications, from search, to product descriptions, to social networks.
Abstract: This article looks at the knowledge graphs of five diverse tech companies, comparing the similarities and differences in their respective experiences of building and using the graphs, and discussing the challenges that all knowledge-driven enterprises face today. The collection of knowledge graphs discussed here covers the breadth of applications, from search, to product descriptions, to social networks.
155 citations
••
14 Aug 2018TL;DR: The authors proposed a model that combines the two approaches to avoid both their deficiencies: first retrieve a response and then refine it, with the final sequence generator treating the retrieval as additional context.
Abstract: Sequence generation models for dialogue are known to have several problems: they tend to produce short, generic sentences that are uninformative and unengaging. Retrieval models on the other hand can surface interesting responses, but are restricted to the given retrieval set leading to erroneous replies that cannot be tuned to the specific context. In this work we develop a model that combines the two approaches to avoid both their deficiencies: first retrieve a response and then refine it – the final sequence generator treating the retrieval as additional context. We show on the recent ConvAI2 challenge task our approach produces responses superior to both standard retrieval and generation models in human evaluations.
155 citations
•
16 Oct 2008TL;DR: In this article, user affinity is based on measuring positive and negative interactions by users as both senders and recipients of messages generated by applications in social networks, which is computed for the different types of messages and interactions provided by applications.
Abstract: Applications in social networks support interaction between members through various types of channels such as notifications, newsfeed, and so forth. For each channel, applications are ranked based on their user affinity measures. User affinity is based on measuring positive and negative interactions by users as both senders and recipients of messages generated by applications. Metrics are computed for the different types of messages and interactions provided by applications. For each channel, an application receives user affinity score based on specific weighted combination of the metrics. Applications use channel resources to send messages to increase their user base. Given the large number of applications that are available, the extent to which applications are allowed to use channels is controlled, limiting their resource consumption. User affinity scores of applications calculated for a channel are used to decide the allocation of channel resources for an application.
155 citations
Authors
Showing all 7875 results
Name | H-index | Papers | Citations |
---|---|---|---|
Yoshua Bengio | 202 | 1033 | 420313 |
Xiang Zhang | 154 | 1733 | 117576 |
Jitendra Malik | 151 | 493 | 165087 |
Trevor Darrell | 148 | 678 | 181113 |
Christopher D. Manning | 138 | 499 | 147595 |
Robert W. Heath | 128 | 1049 | 73171 |
Pieter Abbeel | 126 | 589 | 70911 |
Yann LeCun | 121 | 369 | 171211 |
Li Fei-Fei | 120 | 420 | 145574 |
Jon Kleinberg | 117 | 444 | 87865 |
Sergey Levine | 115 | 652 | 59769 |
Richard Szeliski | 113 | 359 | 72019 |
Sanjeev Kumar | 113 | 1325 | 54386 |
Bruce Neal | 108 | 561 | 87213 |
Larry S. Davis | 107 | 693 | 49714 |