Online Graph Prediction with Random Trees
نویسندگان
چکیده
In online transductive graph prediction a learner is initially given an undirected graph G = (V,E) with unknown binary labels y = (y1, . . . , yn) ∈ {−1,+1}n assigned to the vertices V = {1, . . . , n}. At time t = 1 an arbitrary vertex i1 ∈ V is selected and the learner must predict its label yi1 ∈ {−1,+1}. Then yi1 is revealed and a new vertex i2 6= i1 of V is selected. This process goes on for t = 1, 2, . . . , n until all vertices of G have been selected. The learner’s goal is to minimize the number of prediction mistakes.
منابع مشابه
Providing a Link Prediction Model based on Structural and Homophily Similarity in Social Networks
In recent years, with the growing number of online social networks, these networks have become one of the best markets for advertising and commerce, so studying these networks is very important. Most online social networks are growing and changing with new communications (new edges). Forecasting new edges in online social networks can give us a better understanding of the growth of these networ...
متن کاملFast and Optimal Prediction on a Labeled Tree
We characterize, up to constant factors, the number of mistakes necessary and sufficient for sequentially predicting a given tree with binary labeled nodes. We provide an efficient algorithm achieving this number of mistakes on any tree. Tree prediction algorithms can solve the general graph prediction problem by representing the graph via one of its spanning trees. In order to cope with advers...
متن کاملIsing models on locally tree-like graphs
We consider Ising models on graphs that converge locally to trees. Examples include random regular graphs with bounded degree and uniformly random graphs with bounded average degree. We prove that the ‘cavity’ prediction for the limiting free energy per spin is correct for any temperature and external field. Further, local marginals can be approximated by iterating a set of mean field (cavity) ...
متن کاملThe eccentric connectivity index of bucket recursive trees
If $G$ is a connected graph with vertex set $V$, then the eccentric connectivity index of $G$, $xi^c(G)$, is defined as $sum_{vin V(G)}deg(v)ecc(v)$ where $deg(v)$ is the degree of a vertex $v$ and $ecc(v)$ is its eccentricity. In this paper we show some convergence in probability and an asymptotic normality based on this index in random bucket recursive trees.
متن کاملMondrian Forests: Efficient Online Random Forests
Ensembles of randomized decision trees, usually referred to as random forests, are widely used for classification and regression tasks in machine learning and statistics. Random forests achieve competitive predictive performance and are computationally efficient to train and test, making them excellent candidates for real-world prediction tasks. The most popular random forest variants (such as ...
متن کامل