Fast Neighborhood Subgraph Pairwise Distance Kernel
نویسندگان
چکیده
We introduce a novel graph kernel called the Neighborhood Subgraph Pairwise Distance Kernel. The kernel decomposes a graph into all pairs of neighborhood subgraphs of small radius at increasing distances. We show that using a fast graph invariant we obtain significant speed-ups in the Gram matrix computation. Finally, we test the novel kernel on a wide range of chemoinformatics tasks, from antiviral to anticarcinogenic to toxicological activity prediction, and observe competitive performance when compared against several recent graph kernel methods.
منابع مشابه
ASM Kernel: Graph Kernel using Approximate Subgraph Matching for Relation Extraction
Kernel methods have been widely studied in several natural language processing tasks such as relation extraction and sentence classification. In this work, we present a new graph kernel that is derived from a distance measure described in prior work as Approximate Subgraph Matching (ASM). The classical ASM distance, shown to be effective for event extraction, is not a valid kernel and was prima...
متن کاملLocalization from Pairwise Distance Relationships using Kernel PCA
In this paper, we present a method for estimating the relative localization for a set of points from information indicative of pairwise distance. While other methods for localization have been proposed, we propose an alternative that is simple to implement and easily extendable for different datasets of varied dimensionality. This method utilizes the Kernel PCA framework [6] (or equivantly the ...
متن کاملVC-dimension and Erd\H{o}s-P\'osa property
Let G = (V,E) be a graph. A k-neighborhood in G is a set of vertices consisting of all the vertices at distance at most k from some vertex of G. The hypergraph on vertex set V which edge set consists of all the k-neighborhoods of G for all k is the neighborhood hypergraph of G. Our goal in this paper is to investigate the complexity of a graph in terms of its neighborhoods. Precisely, we define...
متن کاملFast High-dimensional Kernel Summations Using the Monte Carlo Multipole Method
We propose a new fast Gaussian summation algorithm for high-dimensional datasets with high accuracy. First, we extend the original fast multipole-type methods to use approximation schemes with both hard and probabilistic error. Second, we utilize a new data structure called subspace tree which maps each data point in the node to its lower dimensional mapping as determined by any linear dimensio...
متن کاملComposite Kernel Optimization in Semi-Supervised Metric
Machine-learning solutions to classification, clustering and matching problems critically depend on the adopted metric, which in the past was selected heuristically. In the last decade, it has been demonstrated that an appropriate metric can be learnt from data, resulting in superior performance as compared with traditional metrics. This has recently stimulated a considerable interest in the to...
متن کامل