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.

FlowNet3D: Learning Scene Flow in 3D Point Clouds

Abstract: Many applications in robotics and human-computer interaction can benefit from understanding 3D motion of points in a dynamic environment, widely noted as scene flow. While most previous methods focus on stereo and RGB-D images as input, few try to estimate scene flow directly from point clouds. In this work, we propose a novel deep neural network named FlowNet3D that learns scene flow from point clouds in an end-to-end fashion. Our network simultaneously learns deep hierarchical features of point clouds and flow embeddings that represent point motions, supported by two newly proposed learning layers for point sets. We evaluate the network on both challenging synthetic data from FlyingThings3D and real Lidar scans from KITTI. Trained on synthetic data only, our network successfully generalizes to real scans, outperforming various baselines and showing competitive results to the prior art. We also demonstrate two applications of our scene flow output (scan registration and motion segmentation) to show its potential wide use cases.

Systems and methods for providing dynamically selected media content to a user of an electronic device in a social network environment

Abstract: A system and method provides dynamically selected media content to someone using an electronic device in a social network environment. Items of media content are selected for the user based on his or her relationships with one or more other users. The user's relationships with other users are reflected in the selected media content and its format. An order is assigned to the items of media content, for example, based on their anticipated importance to the user, and the items of media content are displayed to the user in the assigned order. The user may change the order of the items of media content. The user's interactions with media content available in the social network environment are monitored, and those interactions are used to select additional items of media content for the user.

Going Deeper in Spiking Neural Networks: VGG and Residual Architectures

Abstract: Over the past few years, Spiking Neural Networks (SNNs) have become popular as a possible pathway to enable low-power event-driven neuromorphic hardware However, their application in machine learning have largely been limited to very shallow neural network architectures for simple problems In this paper, we propose a novel algorithmic technique for generating an SNN with a deep architecture, and demonstrate its effectiveness on complex visual recognition problems such as CIFAR-10 and ImageNet Our technique applies to both VGG and Residual network architectures, with significantly better accuracy than the state-of-the-art Finally, we present analysis of the sparse event-driven computations to demonstrate reduced hardware overhead when operating in the spiking domain

OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs.

Abstract: We study a conversational reasoning model that strategically traverses through a large-scale common fact knowledge graph (KG) to introduce engaging and contextually diverse entities and attributes. For this study, we collect a new Open-ended Dialog KG parallel corpus called OpenDialKG, where each utterance from 15K human-to-human role-playing dialogs is manually annotated with ground-truth reference to corresponding entities and paths from a large-scale KG with 1M+ facts. We then propose the DialKG Walker model that learns the symbolic transitions of dialog contexts as structured traversals over KG, and predicts natural entities to introduce given previous dialog contexts via a novel domain-agnostic, attention-based graph path decoder. Automatic and human evaluations show that our model can retrieve more natural and human-like responses than the state-of-the-art baselines or rule-based models, in both in-domain and cross-domain tasks. The proposed model also generates a KG walk path for each entity retrieved, providing a natural way to explain conversational reasoning.

Uncovering Large Groups of Active Malicious Accounts in Online Social Networks

Abstract: The success of online social networks has attracted a constant interest in attacking and exploiting them. Attackers usually control malicious accounts, including both fake and compromised real user accounts, to launch attack campaigns such as social spam, malware distribution, and online rating distortion. To defend against these attacks, we design and implement a malicious account detection system called SynchroTrap. We observe that malicious accounts usually perform loosely synchronized actions in a variety of social network context. Our system clusters user accounts according to the similarity of their actions and uncovers large groups of malicious accounts that act similarly at around the same time for a sustained period of time. We implement SynchroTrap as an incremental processing system on Hadoop and Giraph so that it can process the massive user activity data in a large online social network efficiently. We have deployed our system in five applications at Facebook and Instagram. SynchroTrap was able to unveil more than two million malicious accounts and 1156 large attack campaigns within one month.