Graph based methods are among the most active and applicable approaches studied in semi-supervised learning. The problem of neighborhood graph construction for these methods is addressed in this paper. Neighborhood graph construction plays a key role in the quality of the classification in graph based methods. Several unsupervised graph construction methods have been proposed that have addresse...

The (p)-neighborhood graph of a graph G, denoted N p (G), is de-ned on the same vertex set as G, with x; y] 2 E (N 2 (G)) if and only if jN(x)\N(y)j p in G, where N (v) is the open neighborhood of vertex v. The p]-neighborhood graph of G, N p G], is deened similarly, using closed neighborhoods rather than open ones. If G is the underlying graph of a symmetric digraph D, then the p-neighborhood ...

The neighborhood graph N(G) of a simple undirected graph G = (V,E) is the graph (V,EN ) where EN = {{a, b} | a 6= b , {x, a} ∈ E and {x, b} ∈ E for some x ∈ V }. It is well-known that the neighborhood graph N(G) is connected if and only if the graph G is connected and non-bipartite. We present some results concerning the k-iterated neighborhood graph N(G) := N(N(. . . N(G))) of G. In particular...

The k-NN graph has played a central role in increasingly popular data-driven techniques for various learning and vision tasks; yet, finding an efficient and effective way to construct k-NN graphs remains a challenge, especially for large-scale high-dimensional data. In this paper, we propose a new approach to construct approximate k-NN graphs with emphasis in: efficiency and accuracy. We hierar...

By an edge-neighborhood of an edge f in a graph we mean the subgraph induced by nodes outside f which are adjacent to some node on f. Connected graphs whose line graphs have the same edge-neighborhood of any edge are characterized. There are P 4 , stars, complete graphs and regular triangle-free graphs in which any two nodes with the distance two have the same number of common neighbors. Object...

The Web Graph represents the structure of the World Wide Web by denoting each web page as a vertex and each hyperlink as an arc. We introduce the concept of the Neighborhood Graph to model the local structure of the Web surrounding a particular web page. We investigate some structural and statistical properties of the Neighborhood Graphs and perform a comparison with the corresponding propertie...

in this paper, we define the common minimal common neighborhooddominating signed graph (or common minimal $cn$-dominating signedgraph) of a given signed graph and offer a structuralcharacterization of common minimal $cn$-dominating signed graphs.in the sequel, we also obtained switching equivalencecharacterization: $overline{sigma} sim cmcn(sigma)$, where$overline{sigma}$ and $cmcn(sigma)$ are ...

A lot of real-life data are of graph nature. However, it is not until recently that business begins to exploit data’s connectedness for business insights. On the other hand, RDBMSs are a mature technology for data management, but they are not for graph processing. Take graph traversal, a common graph operation for example, it heavily relies on a graph primitive that accesses a given node’s neig...