From: A graph-search framework for associating gene identifiers with documents
(1) let Q0 be the probability distribution such that Q0(x) = 1 |
---|
(2) for d = 1, ..., d max do |
• let Q d (x) = 0 for all x |
• for i = 1, ..., m do |
- sample x i according to Qd-1 |
- Q d (x i ) = γQd-1(x i ) |
- for each edge label ℓ ∈ L (x) |
* for each node y ∈ Y(x, ℓ) |
· let q xy = Pr(y|ℓ, x)·Pr(ℓ|x) |
· increment Q d (y) by (1 - γ)Qd-1(x i )q xy |
(3) return (z) as an approximation to Q(z|x) |