# Seeking “gold standard” to evaluate accuracy of network clustering algorithm

I'm currently looking at network clustering algorithms (we're currently looking at both directed and undirected, unweighted networks). The algorithms we've tried produce visually nice clusters. However, we would like to evaluate them against some "gold standard" -- a collection of networks in which the clusters have already been identified (and are more-or-less regarded as the clusters by the complex network's research community).

Question: What are the gold standards for network clustering algorithms? Where can I access them?

• Welcome! What exactly are you asking for: accepted algorithms, algorithms with proven performance or curated test sets? – Raphael Aug 3 '12 at 6:12
• Curated test sets, in particular. Although I'd also be interested in the other items you list. – Douglas S. Stones Aug 3 '12 at 7:39