adm-pres/pres.tex

\documentclass{beamer}
\usetheme[progressbar=frametitle]{metropolis}

% g \in G is explanation as a model
% f is the model we're trying to explain
% does, being model agnostic, means we do not care about specifics of f.
% We use Locally Weighted Square Loss as L, where I suspect pi is the weight and we thus estimate the difference between the actual model
% and our explanation, and multiply this with the proximity of the data point z, to x.
% Spørg lige Lasse hvorfor min(L(f,g,pi_x(z)) + omega(g)) bliver intractable, når omega(g) er en konstant!




\usepackage{setspace}
\usepackage[T1]{fontenc}
\usepackage[sfdefault,scaled=.85]{FiraSans}
%\usepackage{newtxsf}
\usepackage[ruled, linesnumbered]{algorithm2e}
\SetKwInput{kwRequire}{Require}
\SetKw{kwExpl}{explain}

\title{Why Should I Trust You?}
\subtitle{Explaining the Predictions of Any Classifier}
\author{Casper Vestergaard Kristensen \and Alexander Munch-Hansen}
\institute{Aarhus University}
\date{\today}

\begin{document}
\begin{frame}
\titlepage
\end{frame}

\begin{frame}
  \setbeamertemplate{section in toc}[sections numbered]
  \frametitle{Outline}
  \setstretch{0.5}
  \tableofcontents

\end{frame}





\section{Meta information}
%\subsection{Authors}
 
\begin{frame}
\frametitle{Authors}
\begin{itemize}
\item Marco Tulio Ribeiro
\item Sameer Singh
\item Carlos Guestrin
\end{itemize}
\end{frame}

%\subsection{Publishing}

\begin{frame}[fragile]{Metropolis}
  \frametitle{Publishing}
  
  \begin{itemize}
  \item Conference Paper, Research
  \item KDD '16 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
    \begin{itemize}
    \item A premier interdisciplinary conference, brings together researchers and practitioners from data science, data mining, knowledge discovery, large-scale data analytics, and big data.
    \item Sigkdd has the highest h5 index of any conference involving databases or data in general
    \item Highly trusted source
    \end{itemize}
  \end{itemize}
\end{frame}

  \section{Article}

  %\subsection{Problem}

  \begin{frame}
    \frametitle{Problem definition}
    \begin{itemize}
    \item People often use Machine Learning models for predictions
    \item Blindly trusting a prediction can lead to poor decision making
    \item We seek to understand the reasons behind predictions
      \begin{itemize}
      \item As well as the model doing the predictions
      \end{itemize}
    \end{itemize}
  \end{frame}

  \begin{frame}
    \frametitle{Problem definition}
    \begin{itemize}
    \item People often use Machine Learning models for predictions
    \item Blindly trusting a prediction can lead to poor decision making
    \item We seek to understand the reasons behind predictions
      \begin{itemize}
      \item As well as the model doing the predictions
      \end{itemize}
    \end{itemize}
    \center
    \includegraphics[scale=0.2]{graphics/doctor_pred.png}
  \end{frame}

  %\subsection{Previous Solutions}
  \begin{frame}
    \frametitle{Previous Solutions}
    \begin{itemize}
    \item Relying on accuracy based on validation set
    \end{itemize}
  \end{frame}


  \begin{frame}
    \frametitle{A look into two predictions}
    \includegraphics[scale=0.25]{graphics/christ_vs_atheism.png}
  \end{frame}

  \begin{frame}
    \frametitle{A look into two predictions}
    \includegraphics[scale=0.25]{graphics/christ_vs_atheism_annotated_1.png}
  \end{frame}
  
  \begin{frame}
    \frametitle{A look into two predictions}
    \includegraphics[scale=0.25]{graphics/christ_vs_atheism_annotated_2.png}
  \end{frame}

  \subsection{The LIME framework}
  \begin{frame}
    \frametitle{LIME}
    \begin{itemize}
    \item The algorithm created
    \item Explains the predictions of \emph{any} classifier or regressor in a faithful way, by approximating it locally with an \emph{interpretable} model.
    \end{itemize}
  \end{frame}

  \begin{frame}
    \frametitle{Properties of a good explanation}
    \begin{itemize}
    \item It should be \emph{intepretable}:
      \begin{itemize}
      \item They must provide qualitative understanding between the input variables and the response
      \item They must take into account the users limitations
      \item Use a representation understandable to humans
      \item Could be a binary vector indicating presence or absence of a word
      \item Could be a binary vector indicating presence of absence of super-pixels in an image
      \end{itemize}
    \item It should have \emph{fidelity}:
      \begin{itemize}
      \item Essentially means the model should be faithful.
      \item Local fidelity does not imply global fidelity
      \item The explanation should aim to correspond to how the model behaves in the vicinity of the instance being predicted
      \end{itemize}
    \item It should be \emph{model-agnostic}:
      \begin{itemize}
      \item The explanation should be blind to what model is underneath
      \end{itemize}

    \end{itemize}
  \end{frame}
  


  \subsection{Explaining Predictions}
  \begin{frame}
    \frametitle{The Fidelity-Interpretability Trade-off}
    
  \end{frame}
 % \subsubsection{Examples}
  \begin{frame}
    % \frametitle{Sparse Linear Explanations}
    \frametitle{Explaining an individual prediction}
    \begin{algorithm}[H]
      \setstretch{0.9}
\SetAlgoLined
\kwRequire{Classifier $f$, Number of samples $N$}
\kwRequire{Instance $x$, and its intepretable version $x^{\prime}$}
\kwRequire{Similarity kernel $\pi_x$, Length of explanation $K$}
\Indp
 $\mathcal{Z} \leftarrow \{\}$ \\
 \For{$i \in \{1,2,3,\dots, N\}$}{
   $z_i^{\prime} \leftarrow sample\_around(x^{\prime})$ \\
   $\mathcal{Z} \leftarrow \mathcal{Z} \cup  \langle z_i^{\prime}, f(z_i), \pi_{x}(z_i) \rangle$ \\
 }
 $w \leftarrow \text{K-Lasso}(\mathcal{Z},K) \vartriangleright \text{with } z_i^{\prime} \text{ as features, } f(z) \text{ as target}$ \\
\Return $w$
 \caption{Sparse Linear Explanations using LIME}
\end{algorithm}
% This algorithm approximates the minimization problem of computing a single individual explanation of a prediction.
% K-Lasso is the procedure of learning the weights via least squares. Wtf are these weights???
  \end{frame}


  \begin{frame}
    \frametitle{Text Classification}
  \end{frame}

  \begin{frame}
    \frametitle{Deep Networks for Images}
  \end{frame}
  \subsection{Explaining Models}
  
  \begin{frame}
    \frametitle{Submodular Picks}
        \begin{algorithm}[H]
      \setstretch{0.9}
\SetAlgoLined
\kwRequire{Instances $X$, Budget $B$}
\Indp
 \ForAll{$x_i \in X$}{
   $W_i \leftarrow \mathbf{explain}(x_i, x_i^{\prime})$ \qquad \qquad $\vartriangleright$ Using Algorithm 1
 }
 \For{$j \in \{1\dots d^{\prime}$} {
   $I_j \leftarrow \sqrt{\sum_{i=1}^n |W_{ij}|}$ \qquad \qquad \quad $\vartriangleright$ Compute feature importances
 }
 $V \leftarrow \{\}$ \\
 \While(\qquad \qquad \qquad \quad \ \ $\vartriangleright$ Greedy optimisation of Eq 4){$|V| < B$} {
   $V \leftarrow V \cup  \text{argmax}_i \ c(V \cup \{i\}, W, i)$
   }
\Return $V$
 \caption{Submodular pick (SP) algorithm}
\end{algorithm}
  \end{frame}

  \section{Experiments}
  %\subsection{Simulated User Experiments}
  %\subsubsection{Setup}
  \begin{frame}
    \frametitle{Setup}
  \end{frame}
  %\subsection{Human Subjects}

  \section{Conclusion}
  
  \begin{frame}
    \frametitle{Conclusion}
  \end{frame}

  \section{Recap}
  \begin{frame}
    \frametitle{Recap}
  \end{frame}
\end{document}