Facebook

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

Embedding-based Retrieval in Facebook Search

Abstract: Search in social networks such as Facebook poses different challenges than in classical web search: besides the query text, it is important to take into account the searcher's context to provide relevant results. Their social graph is an integral part of this context and is a unique aspect of Facebook search. While embedding-based retrieval (EBR) has been applied in web search engines for years, Facebook search was still mainly based on a Boolean matching model. In this paper, we discuss the techniques for applying EBR to a Facebook Search system. We introduce the unified embedding framework developed to model semantic embeddings for personalized search, and the system to serve embedding-based retrieval in a typical search system based on an inverted index. We discuss various tricks and experiences on end-to-end optimization of the whole system, including ANN parameter tuning and full-stack optimization. Finally, we present our progress on two selected advanced topics about modeling. We evaluated EBR on verticals for Facebook Search with significant metrics gains observed in online A/B experiments. We believe this paper will provide useful insights and experiences to help people on developing embedding-based retrieval systems in search engines.

Creating groups of users in a social networking system

Abstract: A social networking system facilitates a user's creation of a group of other users from among the user's connections in the user's social network. The created groups may be used, for example, to publish information to certain user-defined groups or to define privacy settings or other access rights to the user's content according to such user-defined groups. When a user adds connections to a group, the social networking system determines suggested connections that have not been added to the group, based on a similarity of the suggested connections with one or more of the connections who have been added to the group. These suggested connections are then presented to the user to facilitate the creation of the group. Both positive and negative feedback may be used to generate a useful set of suggestions, which may be updated as the user further defines the group.

Graph cluster randomization: network exposure to multiple universes

Abstract: A/B testing is a standard approach for evaluating the effect of online experiments; the goal is to estimate the `average treatment effect' of a new feature or condition by exposing a sample of the overall population to it. A drawback with A/B testing is that it is poorly suited for experiments involving social interference, when the treatment of individuals spills over to neighboring individuals along an underlying social network. In this work, we propose a novel methodology using graph clustering to analyze average treatment effects under social interference. To begin, we characterize graph-theoretic conditions under which individuals can be considered to be `network exposed' to an experiment. We then show how graph cluster randomization admits an efficient exact algorithm to compute the probabilities for each vertex being network exposed under several of these exposure conditions. Using these probabilities as inverse weights, a Horvitz-Thompson estimator can then provide an effect estimate that is unbiased, provided that the exposure model has been properly specified. Given an estimator that is unbiased, we focus on minimizing the variance. First, we develop simple sufficient conditions for the variance of the estimator to be asymptotically small in n, the size of the graph. However, for general randomization schemes, this variance can be lower bounded by an exponential function of the degrees of a graph. In contrast, we show that if a graph satisfies a restricted-growth condition on the growth rate of neighborhoods, then there exists a natural clustering algorithm, based on vertex neighborhoods, for which the variance of the estimator can be upper bounded by a linear function of the degrees. Thus we show that proper cluster randomization can lead to exponentially lower estimator variance when experimentally measuring average treatment effects under interference.

Generating recommended search queries on online social networks

Abstract: In one embodiment, a method includes accessing a social graph including a number of nodes and a number of edges connecting the nodes. Each of the edges between two of the nodes represent a single degree of separation between them. The nodes include a first node corresponding to a first user associated with an online social network and a number of second nodes that each correspond to a concept or a second user associated with the online social network. The method also includes generating a number of cards. Each card includes a suggested query referencing a query-domain associated with the online social network and zero or more query-filters for the query-domain. Each query-filter references one or more nodes of the number of nodes or one or more edges of the number of edges.

Beyond frontal faces: Improving Person Recognition using multiple cues

Abstract: We explore the task of recognizing peoples' identities in photo albums in an unconstrained setting. To facilitate this, we introduce the new People In Photo Albums (PIPA) dataset, consisting of over 60000 instances of ∼2000 individuals collected from public Flickr photo albums. With only about half of the person images containing a frontal face, the recognition task is very challenging due to the large variations in pose, clothing, camera viewpoint, image resolution and illumination. We propose the Pose Invariant PErson Recognition (PIPER) method, which accumulates the cues of poselet-level person recognizers trained by deep convolutional networks to discount for the pose variations, combined with a face recognizer and a global recognizer. Experiments on three different settings confirm that in our unconstrained setup PIPER significantly improves on the performance of DeepFace, which is one of the best face recognizers as measured on the LFW dataset.