Workshop on Managing and Mining Massive Data (M3D-98)

管理和挖掘海量数据研讨会（M3D-98）的目的是促进一群对开发用于管理和挖掘海量数据集的可扩展系统感兴趣的计算机科学家之间的互动。该研讨会由Robert Grossman（芝加哥伊利诺伊大学）和Reagan Moore（圣地亚哥超级计算机中心）共同组织。研讨会的目标是：确定将数据挖掘扩展到大规模数据集的有前途的方法和技术；研究数据挖掘如何与数据库、数字图书馆、数据仓库和数据档案更紧密地集成；确定如何将数据挖掘服务集成到新兴的国家计算基础设施中；并开始开发适合挖掘海量数据集的社区数据集、基准、交换格式和测试平台的过程。工作坊包括调查讲座、背景讲座、数据挖掘不同方面的技术讲座，以及几个介绍数据挖掘案例研究的应用讲座。此外，还有白皮书描述了基本的挑战和问题、提出的研究议程、测试平台、新兴标准和相关事项。白皮书和相关材料将在研讨会开始前提供给受邀的与会者，并在研讨会结束后大约一个月通过M3D网站提供给公众。

The purpose of the Workshop on Managing and Mining Massive Data (M3D-98) is to foster interactions among an invited group of computer scientists who are interested in developing scalable systems for managing and mining massive data sets. The workshop is co-organized by Robert Grossman (University of Illinois, Chicago) and Reagan Moore (San Diego Supercomputer Center). The goals of the workshop are: to identify promising approaches and technologies for scaling data mining to massive data sets; to investigate how data mining can be more tightly integrated with databases, digital libraries, data warehouses, and data archives; to identify how data mining services can be integrated into the emerging national computational infrastructure; and to begin the process of developing community data sets, benchmarks, interchanged formats, and testbeds appropriate for mining massive data sets. The workshop consists of survey talks, background talks and technical talks on different aspects of data mining as well as several application talks describing data mining case studies. In addition, there are also white papers describing fundamental challenges and issues, proposed research agendas, testbeds, emerging standards, and related matters. The white papers and related materials will be available to the invited participants prior to the workshop and to the general public via a M3D web site approximately a month after the workshop.