arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1708.06000cs.AIcs.CLcs.SI
收藏

无限演化聚类模型的有效在线推理及其在潜在社会事件发现中的应用

Efficient Online Inference for Infinite Evolutionary Cluster models with Applications to Latent Social Event Discovery

Carnegie Mellon University(卡内基梅隆大学);Northeastern University(东北大学)

Wei Wei, Kennth Joseph, Kathleen Carley

摘要:

经常性中国餐馆过程(RCRP)是一种强大的统计方法,用于在大规模社交媒体数据中建模不断变化的集群。使用RCRP,可以允许模型中的聚类数量和聚类参数随时间变化。然而,RCRP的应用在很大程度上受到限制,由于集群进化先验和多项式似然之间的非共轭。这种非共轭性使得推理困难,并限制了使用RCRP的模型的可扩展性,导致RCRP仅适用于简单的问题,例如可以通过单个高斯发射近似的问题。在本文中,我们提供了一个新的解决方案的非共轭问题的RCRP和一个例子,如何利用我们的解决方案的一个特定的问题-社会事件发现问题。通过在推理中使用顺序蒙特卡罗方法,我们的方法可以大规模地扩展,并且具有高度的可扩展性,可以在数千万文档上工作。我们能够生成高质量的主题和位置分布的集群,可以直接解释为真实的社会事件,我们的实验结果表明,所提出的方法实现更好的预测性能比以前的工作中报告的技术。我们还展示了我们开发的技术可以用于更一般的方式来解决类似的问题。

英文摘要:

The Recurrent Chinese Restaurant Process (RCRP) is a powerful statistical method for modeling evolving clusters in large scale social media data. With the RCRP, one can allow both the number of clusters and the cluster parameters in a model to change over time. However, application of the RCRP has largely been limited due to the non-conjugacy between the cluster evolutionary priors and the Multinomial likelihood. This non-conjugacy makes inference di cult and restricts the scalability of models which use the RCRP, leading to the RCRP being applied only in simple problems, such as those that can be approximated by a single Gaussian emission. In this paper, we provide a novel solution for the non-conjugacy issues for the RCRP and an example of how to leverage our solution for one speci c problem - the social event discovery problem. By utilizing Sequential Monte Carlo methods in inference, our approach can be massively paralleled and is highly scalable, to the extent it can work on tens of millions of documents. We are able to generate high quality topical and location distributions of the clusters that can be directly interpreted as real social events, and our experimental results suggest that the approaches proposed achieve much better predictive performance than techniques reported in prior work. We also demonstrate how the techniques we develop can be used in a much more general ways toward similar problems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑