========================================================================
KronFit: estimate Kronecker graphs initiator matrix
========================================================================
KronFit is a fast and scalable algorithm for fitting the Kronecker graph
generation model to large real networks. A naive approach to fitting would
take super-exponential time. In contrast, KronFit takes linear time. KronFit
finds accurate parameters that very well mimic the properties of target
networks. In fact, using just four parameters we can accurately model several
aspects of global network structure.
For more information about the procedure see:
Kronecker Graphs: an approach to modeling networks
Jure Leskovec, Deepayan Chakrabarti, Jon Kleinberg, Christos Faloutsos,
Zoubin Ghahramani.
http://arxiv.org/abs/0812.4905
Depending on the platform (Windows or Linux) you need to edit the Makefile.
Use 'make opt' to compile the optimized (fast) version of the code.
/////////////////////////////////////////////////////////////////////////////
Parameters:
-i:Input graph file (single directed edge per line) (default:'../as20graph.txt')
-o:Output file prefix (default:'')
-n0:Innitiator matrix size (default:2)
-m:Init Gradient Descent Matrix (R=random) (default:'0.9 0.7; 0.5 0.2')
-p:Initial node permutation: d:Degree, r:Random, o:Order (default:'d')
-gi:Gradient descent iterations (default:50)
-l:Learning rate (default:1e-05)
-mns:Minimum gradient step (default:0.005)
-mxs:Maximum gradient step (default:0.05)
-w:Samples to warm up (default:10000)
-s:Samples per gradient estimation (default:100000)
-sim:Scale the initiator to match the number of edges (default:'T')
-nsp:Probability of using NodeSwap (vs. EdgeSwap) MCMC proposal distribution (default:1)
/////////////////////////////////////////////////////////////////////////////
Usage:
Estimate the 2-by-2 Kronecker initiator matrix for the Autonomous Systems
network using 100 gradient descent iterations. We initialize the fitting with
the [0.9 0.6; 0.6 0.1] initiator matrix.
kronfit -i:../as20graph.txt -n0:2 -m:"0.9 0.6; 0.6 0.1" -gi:100
Snap-09-11-25.zip_snap_snap stanford_snap斯坦福_社会网络分析_算法包
版权申诉
189 浏览量
2022-09-24
01:37:49
上传
评论
收藏 718KB ZIP 举报
Snap-09-11-25.zip_snap_snap stanford_snap斯坦福_社会网络分析_算法包 （205个子文件） 
wikinet.cpp 161KB memes.cpp 139KB unicode.cpp 93KB kronecker.cpp 92KB signnet.cpp 77KB timenet.cpp 62KB dt.cpp 59KB ncp.cpp 59KB linalg.cpp 55KB xml.cpp 46KB tm.cpp 44KB html.cpp 39KB exp.cpp 38KB xmath.cpp 37KB ff.cpp 35KB gnuplot.cpp 31KB lx.cpp 29KB sir.cpp 27KB os.cpp 25KB http.cpp 24KB util.cpp 24KB spinn3r.cpp 22KB fl.cpp 22KB graph.cpp 20KB gstat.cpp 19KB blobbs.cpp 17KB ggen.cpp 17KB wgtnet.cpp 16KB ss.cpp 15KB imdbnet.cpp 15KB gsvd.cpp 14KB ghash.cpp 14KB memenet.cpp 14KB url.cpp 14KB zipfl.cpp 13KB mkdatasets.cpp 13KB arxiv.cpp 12KB md5.cpp 9KB xfl.cpp 8KB env.cpp 8KB trawling.cpp 8KB pp.cpp 7KB bits.cpp 6KB cncom.cpp 5KB statplot.cpp 5KB unicodestring.cpp 4KB macro.cpp 4KB testgraph.cpp 4KB kronfit.cpp 4KB mxdag.cpp 3KB prolog.cpp 3KB hash.cpp 3KB bd.cpp 3KB netstat.cpp 3KB concomp.cpp 2KB netevol.cpp 2KB dblp.cpp 2KB console.cpp 2KB anf.cpp 2KB gio.cpp 2KB ut.cpp 2KB subgraph.cpp 2KB base.cpp 2KB gbase.cpp 2KB testSnap.cpp 2KB gviz.cpp 1KB forestfire.cpp 1KB wch.cpp 1KB krongen.cpp 1KB Snap.cpp 683B stdafx.cpp 299B stdafx.cpp 297B stdafx.cpp 296B stdafx.cpp 296B stdafx.cpp 295B stdafx.cpp 295B stdafx.cpp 294B xdt.cpp 250B stdafx.cpp 21B app.cpp 2B alg.cpp 0B unicode.h 167KB ds.h 74KB network.h 56KB dt.h 55KB shash.h 52KB bignet.h 45KB hash.h 44KB gnuplot.h 23KB graph.h 23KB signnet.h 23KB linalg.h 22KB wikinet.h 21KB fl.h 19KB gstat.h 18KB kronecker.h 17KB xmath.h 17KB memes.h 17KB ghash.h 17KB xml.h 16KB共 205 条
- 1
- 2
- 3
资源评论
