libDAI - A free/open source C++ library for Discrete Approximate Inference

Version: 0.3.0 Date: July 12, 2011 See also: http://www.libdai.org

License

libDAI is free software; you can redistribute it and/or modify it under the terms of the BSD 2-clause license (also known as the FreeBSD license), which can be found in the accompanying LICENSE file.

[Note: up to and including version 0.2.7, libDAI was licensed under the GNU General Public License (GPL) version 2 or higher.]

Citing libDAI

If you write a scientific paper describing research that made substantive use of this library, please cite the following paper describing libDAI:

Joris M. Mooij; libDAI: A free & open source C++ library for Discrete Approximate Inference in graphical models; Journal of Machine Learning Research, 11(Aug):2169-2173, 2010.

In BiBTeX format (for your convenience):

@article{Mooij_libDAI_10, author = {Joris M. Mooij}, title = {lib{DAI}: A Free and Open Source {C++} Library for Discrete Approximate Inference in Graphical Models}, journal = {Journal of Machine Learning Research}, year = 2010, month = Aug, volume = 11, pages = {2169-2173}, url = "http://www.jmlr.org/papers/volume11/mooij10a/mooij10a.pdf" }

Moreover, as a personal note, I would appreciate it to be informed about any publications using libDAI at joris dot mooij at libdai dot org.

About libDAI

libDAI is a free/open source C++ library that provides implementations of various (approximate) inference methods for discrete graphical models. libDAI supports arbitrary factor graphs with discrete variables; this includes discrete Markov Random Fields and Bayesian Networks.

The library is targeted at researchers. To be able to use the library, a good understanding of graphical models is needed.

The best way to use libDAI is by writing C++ code that invokes the library; in addition, part of the functionality is accessibly by using the

command line interface
(limited) MatLab interface
(experimental) python interface
(experimental) octave interface.

libDAI can be used to implement novel (approximate) inference algorithms and to easily compare the accuracy and performance with existing algorithms that have been implemented already.

A solver using libDAI was amongst the three winners of the UAI 2010 Approximate Inference Challenge (see http://www.cs.huji.ac.il/project/UAI10/ for more information). The full source code is provided as part of the library.

Features

Currently, libDAI supports the following (approximate) inference methods:

Exact inference by brute force enumeration;
Exact inference by junction-tree methods;
Mean Field;
Loopy Belief Propagation [KFL01];
Fractional Belief Propagation [WiH03];
Tree-Reweighted Belief Propagation [WJW03];
Tree Expectation Propagation [MiQ04];
Generalized Belief Propagation [YFW05];
Double-loop GBP [HAK03];
Various variants of Loop Corrected Belief Propagation [MoK07, MoR05];
Gibbs sampler;
Conditioned Belief Propagation [EaG09];
Decimation algorithm.

These inference methods can be used to calculate partition sums, marginals over subsets of variables, and MAP states (the joint state of variables that has maximum probability).

In addition, libDAI supports parameter learning of conditional probability tables by Expectation Maximization.

Limitations

libDAI is not intended to be a complete package for approximate inference. Instead, it should be considered as an "inference engine", providing various inference methods. In particular, it contains no GUI, currently only supports its own file format for input and output (although support for standard file formats may be added later), and provides very limited visualization functionalities. The only learning method supported currently is Expectation Maximization (or Maximum Likelihood if no data is missing) for learning factor parameters.

Rationale

In my opinion, the lack of open source "reference" implementations hampers progress in research on approximate inference. Methods differ widely in terms of quality and performance characteristics, which also depend in different ways on various properties of the graphical models. Finding the best approximate inference method for a particular application therefore often requires empirical comparisons. However, implementing and debugging these methods takes a lot of time which could otherwise be spent on research. I hope that this code will aid researchers to be able to easily compare various (existing as well as new) approximate inference methods, in this way accelerating research and stimulating real-world applications of approximate inference.

Language

Because libDAI is implemented in C++, it is very fast compared with implementations in MatLab (a factor 1000 faster is not uncommon). libDAI does provide a (limited) MatLab interface for easy integration with MatLab. It also provides a command line interface and experimental python and octave interfaces (thanks to Patrick Pletscher).

Compatibility

The code has been developed under Debian GNU/Linux with the GCC compiler suite. libDAI compiles successfully with g++ versions 3.4 up to 4.6.

libDAI has also been successfully compiled with MS Visual Studio 2008 under Windows (but not all build targets are supported yet) and with Cygwin under Windows.

Finally, libDAI has been compiled successfully on MacOS X.

Downloading libDAI

The libDAI sources and documentation can be downloaded from the libDAI website: http://www.libdai.org.

Mailing list

The Google group "libDAI" (http://groups.google.com/group/libdai) can be used for getting support and discussing development issues.

Building libDAI under UNIX variants (Linux / Cygwin / Mac OS X)

Preparations

You need:

a recent version of gcc (at least version 3.4)
GNU make
recent boost C++ libraries (at least version 1.37; however, version 1.37 shipped with Ubuntu 9.04 is known not to work)
GMP library (or the Windows port called MPIR)
doxygen (only for building the documentation)
graphviz (only for using some of the libDAI command line utilities)
CImg library (only for building the image segmentation example)

On Debian/Ubuntu, you can easily install the required packages with a single command:

apt-get install g++ make doxygen graphviz libboost-dev libboost-graph-dev libboost-program-options-dev libboost-test-dev libgmp-dev cimg-dev

(root permissions needed).

On Mac OS X (10.4 is known to work), these packages can be installed easily via MacPorts. If MacPorts is not already installed, install it according to the instructions at http://www.macports.org/. Then, a simple

sudo port install gmake boost gmp doxygen graphviz

should be enough to install everything that is needed.

On Cygwin, the prebuilt Cygwin package boost-1.33.1-x is known not to work. You can however obtain the latest boost version (you need at least 1.37.0) from http://www.boost.org/ and build it as described in the next subsection.

Building boost under Cygwin

Download the latest boost libraries from http://www.boost.org

Build the required boost libraries using:

./bootstrap.sh --with-libraries=program_options,math,graph,test --prefix=/boost_root/
./bjam

In order to use dynamic linking, the boost .dll's should be somewhere in the path. This can be achieved by a command like:
```
export PATH=$PATH:/boost_root/stage/lib
```

Building libDAI

To build the libDAI source, first copy a template Makefile.* to Makefile.conf (for example, copy Makefile.LINUX to Makefile.conf if you use GNU/Linux). Then, edit the Makefile.conf template to adapt it to your local setup. In case you want to use Boost libraries which are installed in non-standard locations, you have to tell the compiler and linker about their locations (using the -I, -L flags for GCC; also you may need to set the LD_LIBRARY_PATH environment variable correctly before running libDAI binaries). Platform independent build options can be set in Makefile.ALL. Finally, run

make

The build includes a regression test, which may take a while to complete.

If the build is successful, you can test the example program:

examples/example tests/alarm.fg

or the more extensive test program:

tests/testdai --aliases tests/aliases.conf --filename tests/alarm.fg --methods JTREE_HUGIN BP_SEQMAX

Building libDAI under Windows

Preparations

You need:

A recent version of MicroSoft Visual Studio (2008 is known to work)
recent boost C++ libraries (version 1.37 or higher)
GMP or MPIR library
GNU make (can be obtained from http://gnuwin32.sourceforge.net)
CImg library (only for building the image segmentation example)

For the regression test, you need:

GNU diff, GNU sed (can be obtained from http://gnuwin32.sourceforge.net)

Building boost under Windows

Because building boost under Windows is tricky, I provide some guidance here.

Download the boost zip file from http://www.boost.org/users/download and unpack it somewhere.
Download the bjam executable from http://www.boost.org/users/download and unpack it somewhere else.
Download Boost.Build (v2) from http://www.boost.org/docs/tools/build/ index.html and unpack it yet somewhere else.
Edit the file boost-build.jam in the main boost directory to change the BOOST_BUILD directory to the place where you put Boost.Build (use UNIX / instead of W

LibDAI

Install / Use

README