|
@@ -1,7 +1,9 @@
|
|
\subsection{Idea}
|
|
\subsection{Idea}
|
|
\begin{frame}{Basics of PageRank}
|
|
\begin{frame}{Basics of PageRank}
|
|
|
|
+ We all know that:
|
|
\begin{itemize}[<+->]
|
|
\begin{itemize}[<+->]
|
|
\item Humans know what is good for them
|
|
\item Humans know what is good for them
|
|
|
|
+ \item[\xmark] Machines don't know what's good for humans
|
|
\item Humans create Websites
|
|
\item Humans create Websites
|
|
\item Humans will only \href{http://en.wikipedia.org/wiki/Hyperlink}{link} to Websites they like
|
|
\item Humans will only \href{http://en.wikipedia.org/wiki/Hyperlink}{link} to Websites they like
|
|
\item[$\Rightarrow$] Hyperlinks are a quality indicator
|
|
\item[$\Rightarrow$] Hyperlinks are a quality indicator
|
|
@@ -12,8 +14,8 @@
|
|
\begin{itemize}[<+->]
|
|
\begin{itemize}[<+->]
|
|
\item Simply count number of links to a Website
|
|
\item Simply count number of links to a Website
|
|
\item[\xmark] 10,000 links from only one page
|
|
\item[\xmark] 10,000 links from only one page
|
|
- \item Count numbers of Websites that link to a Website
|
|
|
|
- \item[\xmark] Quality of the page matters
|
|
|
|
|
|
+ \item Count number of Websites that link to a Website
|
|
|
|
+ \item[\xmark] Quality of the linking website matters
|
|
\item[\xmark] Total number of links on the source page matters
|
|
\item[\xmark] Total number of links on the source page matters
|
|
\end{itemize}
|
|
\end{itemize}
|
|
\end{frame}
|
|
\end{frame}
|
|
@@ -42,21 +44,28 @@
|
|
\end{algorithmic}
|
|
\end{algorithmic}
|
|
\end{frame}
|
|
\end{frame}
|
|
|
|
|
|
-\begin{frame}{Ants}
|
|
|
|
- \begin{itemize}[<+->]
|
|
|
|
- \item Websites = nodes = anthill
|
|
|
|
- \item Links = edges = paths
|
|
|
|
- \item You place ants on each node
|
|
|
|
- \item They walk over the paths
|
|
|
|
- \item[] (at random, they are ants!)
|
|
|
|
- \item After some time, some anthills will have more ants than
|
|
|
|
- others
|
|
|
|
- \item Those hills are more attractive than others
|
|
|
|
- \item \# ants is probability that a random user would end on
|
|
|
|
- a website
|
|
|
|
- \end{itemize}
|
|
|
|
|
|
+\begin{frame}{What is PageRank?}
|
|
|
|
+ The PageRank algorithm calculates the probability of a randomly
|
|
|
|
+ clicking user ending up on a given page.
|
|
\end{frame}
|
|
\end{frame}
|
|
|
|
|
|
|
|
+\input{Animation}
|
|
|
|
+
|
|
|
|
+%\begin{frame}{Ants}
|
|
|
|
+% \begin{itemize}[<+->]
|
|
|
|
+% \item Websites = nodes = anthill
|
|
|
|
+% \item Links = edges = paths
|
|
|
|
+% \item You place ants on each node
|
|
|
|
+% \item They walk over the paths
|
|
|
|
+% \item[] (at random, they are ants!)
|
|
|
|
+% \item After some time, some anthills will have more ants than
|
|
|
|
+% others
|
|
|
|
+% \item Those hills are more attractive than others
|
|
|
|
+% \item \# ants is probability that a random user would end on
|
|
|
|
+% a website
|
|
|
|
+% \end{itemize}
|
|
|
|
+%\end{frame}
|
|
|
|
+
|
|
\begin{frame}{Mathematics}
|
|
\begin{frame}{Mathematics}
|
|
Let $x$ be a web page. Then
|
|
Let $x$ be a web page. Then
|
|
\begin{itemize}
|
|
\begin{itemize}
|
|
@@ -72,19 +81,19 @@
|
|
\begin{frame}{Pseudocode}
|
|
\begin{frame}{Pseudocode}
|
|
\begin{algorithmic}
|
|
\begin{algorithmic}
|
|
\alertline<1> \Function{PageRank}{Graph $web$, double $q=0.15$, int $iterations$} %q is a damping factor
|
|
\alertline<1> \Function{PageRank}{Graph $web$, double $q=0.15$, int $iterations$} %q is a damping factor
|
|
-\alertline<2> \ForAll{$page \in web$}
|
|
|
|
-\alertline<3> \State $page.pageRank = \frac{1}{|web|}$ \Comment{intial probability}
|
|
|
|
-\alertline<2> \EndFor
|
|
|
|
|
|
+%\alertline<2> \ForAll{$page \in web$}
|
|
|
|
+%\alertline<3> \State $page.pageRank = \frac{1}{|web|}$ \Comment{intial probability}
|
|
|
|
+%\alertline<2> \EndFor
|
|
|
|
|
|
-\alertline<4> \While{$iterations > 0$}
|
|
|
|
-\alertline<5> \ForAll{$page \in web$} \Comment{calculate pageRank of $page$}
|
|
|
|
-\alertline<6> \State $page.pageRank = q$
|
|
|
|
-\alertline<7> \ForAll{$y \in L(page)$}
|
|
|
|
-\alertline<8> \State $page.pageRank$ += $\frac{y.pageRank}{C(y)}$
|
|
|
|
-\alertline<7> \EndFor
|
|
|
|
-\alertline<5> \EndFor
|
|
|
|
-\alertline<4> \State $iterations$ -= $1$
|
|
|
|
-\alertline<4> \EndWhile
|
|
|
|
|
|
+\alertline<2> \While{$iterations > 0$}
|
|
|
|
+\alertline<3> \ForAll{$page \in web$} \Comment{calculate pageRank of $page$}
|
|
|
|
+\alertline<4> \State $page.pageRank = q$
|
|
|
|
+\alertline<5> \ForAll{$y \in L(page)$}
|
|
|
|
+\alertline<6> \State $page.pageRank$ += $\frac{y.pageRank}{C(y)}$
|
|
|
|
+\alertline<5> \EndFor
|
|
|
|
+\alertline<3> \EndFor
|
|
|
|
+\alertline<2> \State $iterations$ -= $1$
|
|
|
|
+\alertline<2> \EndWhile
|
|
\alertline<1> \EndFunction
|
|
\alertline<1> \EndFunction
|
|
\end{algorithmic}
|
|
\end{algorithmic}
|
|
\end{frame}
|
|
\end{frame}
|