Modern recommendation systems in industry often use deep learning (DL) models that achieve better model accuracy with more data and model parameters. However, current opensource DL frameworks, such as TensorFlow and PyTorch, show relatively low scalability on training recommendation models with terabytes of parameters. To efficiently learn large-scale recommendation models from data streams that generate hundreds of terabytes training data daily, we introduce a continual learning system called Kraken. Kraken contains a special parameter server implementation that dynamically adapts to the rapidly changing set of sparse features for the continual training and serving of recommendation models. Kraken provides a sparsity-aware training system that uses different learning optimizers for dense and sparse parameters to reduce memory overhead. Extensive experiments using real-world datasets confirm the effectiveness and scalability of Kraken. Kraken can benefit the accuracy of recommendation tasks with the same memory resources, or trisect the memory usage while keeping model performance.

How can web services that depend on user generated content discern fraudulent input by spammers from legitimate input? In this paper we focus on the social network Facebook and the problem of discerning ill-gotten Page Likes, made by spammers hoping to turn a profit, from legitimate Page Likes. Our method, which we refer to as CopyCatch, detects lockstep Page Like patterns on Facebook by analyzing only the social graph between users and Pages and the times at which the edges in the graph (the Likes) were created. We offer the following contributions: (1) We give a novel problem formulation, with a simple concrete definition of suspicious behavior in terms of graph structure and edge constraints. (2) We offer two algorithms to find such suspicious lockstep behavior - one provably-convergent iterative algorithm and one approximate, scalable MapReduce implementation. (3) We show that our method severely limits "greedy attacks" and analyze the bounds from the application of the Zarankiewicz problem to our setting. Finally, we demonstrate and discuss the effectiveness of CopyCatch at Facebook and on synthetic data, as well as potential extensions to anomaly detection problems in other domains. CopyCatch is actively in use at Facebook, searching for attacks on Facebook's social graph of over a billion users, many millions of Pages, and billions of Page Likes.

Previous studies on search engine click modeling have identified two presentation factors that affect users' behavior: (1) position bias: the same result will get a different number of clicks when displayed in different positions and (2) externalities: the same result might get more clicks when displayed with results of relatively lower quality than when shown with higher quality results. In this paper we focus on analyzing the sequence of user actions to model users' click behavior on sponsored listings shown on the search results page. We first show that temporal click sequences are good indicators of externalities in the advertising domain. We then describe the positional rationality hypothesis to explain both the position bias and the externalities, and based on this hypothesis we further propose the temporal click model (TCM), a Bayesian framework that is scalable and computationally efficient. To the best of our knowledge, this is the first attempt in the literature to estimate positional bias, externalities and unbiased user-perceived ad quality from user click logs in a combined model. We finally evaluate the proposed model on two real datasets, each containing over 100 million ad impressions obtained from a commercial search engine. The experimental results show that TCM outperforms two other competitive methods at click prediction.

The ability to quickly compute hand geometry measurements from a freely posed hand offers advantages to biometric identification systems. While hand geometry systems are not new, typical measurements of lengths and widths of fingers and palms require rigid placement of the hand against pegs. Slight deviations in hand position, finger stretch or pressure can yield different measurements. This paper offers novel approaches to computing hand geometry measurements from frontal views of freely posed hands. These approaches offer advantages in hygiene, comfort and reliability. Our algorithms segment the hand from a known background under spot lights and locate feature points along the fingers and wrists. Given a database of 54 hand images, with three different images of the same hand of each subject, our approach uniquely identified a previously unseen hand with an overall accuracy of 92%.

The problem investigated in this paper is the quick identification of free-form 2D objects using a coefficient based indexing technique. We demonstrate that combining implicit polynomial shape descriptors with calibration techniques has the potential to quickly identify images of similar shapes. As a pilot experiment, our approach is evaluated against a small database consisting of 15 images, with three different images from five categories. The index system achieves an overall top-3 matching accuracy of 88.9% comparing to 91.1% of the traditional brutal force method on the same database with a computational cutoff of 67.7%.

MOTIVATION: During the next phase of the Human Genome Project, research will focus on functional studies of attributing functions to genes, their regulatory elements, and other DNA sequences. To facilitate the use of genomic information in such studies, a new modeling perspective is needed to examine and study genome sequences in the context of many kinds of biological information. Pathways are the logical format for modeling and presenting such information in a manner that is familiar to biological researchers. RESULTS: In this paper we present an integrated system, called Pathways Database System, with a set of software tools for modeling, storing, analyzing, visualizing, and querying biological pathways data at different levels of genetic, molecular, biochemical and organismal detail. The novel features of the system include: (a) genomic information integrated with other biological data and presented from a pathway, rather than from the DNA sequence, perspective; (b) design for biologists who are possibly unfamiliar with genomics, but whose research is essential for annotating gene and genome sequences with biological functions; (c) database design, implementation and graphical tools which enable users to visualize pathways data in multiple abstraction levels, and to pose predetermined queries; and (d) an implementation that allows for web(XML)-based dissemination of query outputs (i.e. pathways data) to researchers in the community, giving them control on the use of pathways data. AVAILABILITY: Available on request from the authors.