arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1805.08901cs.ITmath.IT
收藏

带有辅助信息的社区发现:随机块模型下的精确恢复

Community Detection with Side Information: Exact Recovery under the Stochastic Block Model

Hussein Saad, Aria Nosratinia

摘要:

社区发现问题涉及基于观察图的边缘来对图中的节点标签进行推断。研究了具有$n$节点的二元随机块模型中附加的非图形边信息对精确恢复相变的影响。当边信息由错误概率为$α$的噪声标签组成时,证明了当且仅当$\log(\frac{1-α}α)=Ω(\log(n))$ .当边信息包括揭示一部分$1-ε$的标签,它表明,相变得到改善,当且仅当$\log(1/ε)=Ω(\log(n))$。对于由$K$特征组成的更一般的边信息,研究了两种情况:(1)~ $K$是固定的,而每个特征相对于对应节点标签的似然性随着$n$而演变,以及(2)~特征的数量$K$随着$n$而变化,但每个特征的似然性是固定的。在每种情况下,我们发现边信息何时改善了精确的恢复相变以及改善了多少。除一种特殊情况外,所计算的精确恢复的充分必要条件是严格的。在推导内界的过程中,提出了一种有效的社区发现算法的变体,该算法使用部分恢复算法与局部改进过程相结合。

英文摘要:

The community detection problem involves making inferences about node labels in a graph, based on observing the graph edges. This paper studies the effect of additional, non-graphical side information on the phase transition of exact recovery in the binary stochastic block model (SBM) with $n$ nodes. When side information consists of noisy labels with error probability $α$, it is shown that phase transition is improved if and only if $\log(\frac{1-α}α)=Ω(\log(n))$. When side information consists of revealing a fraction $1-ε$ of the labels, it is shown that phase transition is improved if and only if $\log(1/ε)=Ω(\log(n))$. For a more general side information consisting of $K$ features, two scenarios are studied: (1)~$K$ is fixed while the likelihood of each feature with respect to corresponding node label evolves with $n$, and (2)~The number of features $K$ varies with $n$ but the likelihood of each feature is fixed. In each case, we find when side information improves the exact recovery phase transition and by how much. The calculated necessary and sufficient conditions for exact recovery are tight except for one special case. In the process of deriving inner bounds, a variation of an efficient algorithm is proposed for community detection with side information that uses a partial recovery algorithm combined with a local improvement procedure.

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。

↑