Online selection of diverse results

WSDM 2012
Online selection of diverse results
Debmalya Panigrahi, Atish Das Sarma, Gagan Aggarwal, Andrew Tomkins
Abstract

The phenomenal growth in the volume of easily accessible information via various web-based services has made it essential for service providers to provide users with personalized representative summaries of such information.

Further, online commercial services including social networking and micro-blogging websites, e-commerce portals, leisure and entertainment websites, etc. recommend interesting content to users that is simultaneously diverse on many different axes such as topic, geographic specificity, etc.

The key algorithmic question in all these applications is the generation of a succinct, representative, and relevant summary from a large stream of data coming from a variety of sources. In this paper, we formally model this optimization problem, identify its key structural characteristics, and use these observations to design an extremely scalable and efficient algorithm.

We analyze the algorithm using theoretical techniques to show that it always produces a nearly optimal solution. In addition, we perform large-scale experiments on both real-world and synthetically generated datasets, which confirm that our algorithm performs even better than its analytical guarantees in practice, and also outperforms other candidate algorithms for the problem by a wide margin.

Another publication from the same category: Machine Learning and Data Science

Washinton DC, 27-30 Oct. 2014

Astro: A Predictive Model for Anomaly Detection and Feedback-based Scheduling on Hadoop

Chaitali Gupta, Mayank Bansal, Tzu-Cheng Chuang, Ranjan Sinha, Sami Ben-romdhane

The sheer growth in data volume and Hadoop cluster size make it a significant challenge to diagnose and locate problems in a production-level cluster environment efficiently and within a short period of time. Often times, the distributed monitoring systems are not capable of detecting a problem well in advance when a large-scale Hadoop cluster starts to deteriorate i n performance or becomes unavailable. Thus, inc o m i n g workloads, scheduled between the time when cluster starts to deteriorate and the time when the problem is identified, suffer from longer execution times. As a result, both reliability and throughput of the cluster reduce significantly. In this paper, we address this problem by proposing a system called Astro, which consists of a predictive model and an extension to the Hadoop scheduler. The predictive model in Astro takes into account a rich set of cluster behavioral information that are collected by monitoring processes and model them using machine learning algorithms to predict future behavior of the cluster. The Astro predictive model detects anomalies in the cluster and also identifies a ranked set of metrics that have contributed the most towards the problem. The Astro scheduler uses the prediction outcome and the list of metrics to decide whether it needs to move and reduce workloads from the problematic cluster nodes or to prevent additional workload allocations to them, in order to improve both throughput and reliability of the cluster. The results demonstrate that the Astro scheduler improves usage of cluster compute resources significantly by 64.23% compared to traditional Hadoop. Furthermore, the runtime of the benchmark application reduced by 26.68% during the time of anomaly, thus improving the cluster throughput.

Keywords