arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.01586cs.SIcs.DS
收藏

动态社会流上实时的影响力最大化

Real-Time Influence Maximization on Dynamic Social Streams

Yanhao Wang, Qi Fan, Yuchen Li, Kian-Lee Tan

摘要:

影响力最大化(Influence Maximization,IM)是一个基本问题,它选择一组$k$用户(称为种子)来最大化在社交网络上的影响力,广泛应用于病毒式营销和网络监控。现有的IM解决方案未能考虑社会影响的高度动态性质,这导致网络演化时种子质量差或处理时间长。为了解决这个问题,我们定义了一个新的IM查询命名为流影响力最大化(SIM)的社会流。技术上,SIM采用滑动窗口模型,并维护一组对最近的社交行为具有最大影响值的$k$种子。接下来,我们提出了影响检查点(IC)框架,以促进连续SIM查询处理。IC框架为每个窗口幻灯片创建检查点,并确保获得$\varepsilon$近似解。为了提高其效率,我们进一步设计了一个稀疏影响检查点(SIC)框架,选择性地保持$O(\frac{\log{N}}β)$检查点的大小$N$的滑动窗口,并保持一个$\frac{\varepsilon(1-β)}{2}$近似的解决方案。在真实世界和合成数据集上的实验结果证实了我们提出的框架对最先进的IM方法的有效性和效率。

英文摘要:

Influence maximization (IM), which selects a set of $k$ users (called seeds) to maximize the influence spread over a social network, is a fundamental problem in a wide range of applications such as viral marketing and network monitoring. Existing IM solutions fail to consider the highly dynamic nature of social influence, which results in either poor seed qualities or long processing time when the network evolves. To address this problem, we define a novel IM query named Stream Influence Maximization (SIM) on social streams. Technically, SIM adopts the sliding window model and maintains a set of $k$ seeds with the largest influence value over the most recent social actions. Next, we propose the Influential Checkpoints (IC) framework to facilitate continuous SIM query processing. The IC framework creates a checkpoint for each window slide and ensures an $\varepsilon$-approximate solution. To improve its efficiency, we further devise a Sparse Influential Checkpoints (SIC) framework which selectively keeps $O(\frac{\log{N}}β)$ checkpoints for a sliding window of size $N$ and maintains an $\frac{\varepsilon(1-β)}{2}$-approximate solution. Experimental results on both real-world and synthetic datasets confirm the effectiveness and efficiency of our proposed frameworks against the state-of-the-art IM approaches.

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。

↑