English
Related papers

Related papers: Revisiting classical results on kernels in digraph…

200 papers

These notes provide a self-contained introduction to kernel methods and their geometric foundations in machine learning. Starting from the construction of Hilbert spaces, we develop the theory of positive definite kernels, reproducing…

We consider positive semidefinite kernels valued in the $*$-algebra of adjointable operators on a VE-space (Vector Euclidean space) and that are invariant under actions of $*$-semigroups. A rather general dilation theorem is stated and…

Functional Analysis · Mathematics 2017-02-06 Serdar Ay , Aurelian Gheondea

The seminal theorem of I.J. Schoenberg characterizes positive definite (p.d.) kernels on the unit sphere $S^{n-1}$ invariant under the automorphisms of the sphere. We obtain two generalizations of this theorem for p.d. kernels on fiber…

Classical Analysis and ODEs · Mathematics 2019-04-05 Olga Kuryatnikova , Juan C. Vera

Subgraph representation learning has been effective in solving various real-world problems. However, current graph neural networks (GNNs) produce suboptimal results for subgraph-level tasks due to their inability to capture complex…

Machine Learning · Computer Science 2025-11-12 Dongkwan Kim , Alice Oh

The theory of abstract kernels in non-trivial extensions for many kinds of algebraical objects, such as groups, rings and graded rings, associative algebras, Lie algebras, restricted Lie algebras, DG-algebras and DG-Lie algebras, has been…

Algebraic Topology · Mathematics 2020-05-21 Zelong Li

The success of kernel methods has initiated the design of novel positive semidefinite functions, in particular for structured data. A leading design paradigm for this is the convolution kernel, which decomposes structured objects into their…

Machine Learning · Computer Science 2017-02-01 Nils M. Kriege , Pierre-Louis Giscard , Richard C. Wilson

A {\em quasi-kernel} of a digraph $D$ is an independent set $Q\subseteq V(D)$ such that for every vertex $v\in V(D)\backslash Q$, there exists a directed path with one or two arcs from $v$ to a vertex $u\in Q$. In 1974, Chv\'{a}tal and…

Combinatorics · Mathematics 2022-07-26 Jiangdong Ai , Stefanie Gerke , Gregory Gutin , Anders Yeo , Yacong Zhou

This is a tutorial and survey paper on kernels, kernel methods, and related fields. We start with reviewing the history of kernels in functional analysis and machine learning. Then, Mercer kernel, Hilbert and Banach spaces, Reproducing…

Machine Learning · Statistics 2021-06-17 Benyamin Ghojogh , Ali Ghodsi , Fakhri Karray , Mark Crowley

We present a polyhedral description of kernels in orientations of line multigraphs. Given a digraph $D$, let $FK(D)$ denote the fractional kernel polytope defined on $D$, and let ${\sigma}(D)$ denote the linear system defining $FK(D)$. A…

Combinatorics · Mathematics 2015-10-08 Han Xiao

Graph kernels are usually defined in terms of simpler kernels over local substructures of the original graphs. Different kernels consider different types of substructures. However, in some cases they have similar predictive performances,…

Machine Learning · Computer Science 2016-07-22 Nicolò Navarin , Alessandro Sperduti , Riccardo Tesselli

In the framework of idempotent mathematics, analogs of the classical kernel theorems of L. Schwartz and A. Grothendieck are studied. Idempotent versions of nuclear spaces (in the sense of A. Grothendieck) are discussed. The so-called…

Functional Analysis · Mathematics 2007-05-23 G. L. Litvinov , G. B. Shpiz

Kernel methods are among the most popular techniques in machine learning. From a frequentist/discriminative perspective they play a central role in regularization theory as they provide a natural choice for the hypotheses space and the…

Machine Learning · Statistics 2012-04-17 Mauricio A. Alvarez , Lorenzo Rosasco , Neil D. Lawrence

For a fixed simple digraph $H$ without isolated vertices, we consider the problem of deleting arcs from a given tournament to get a digraph which does not contain $H$ as an immersion. We prove that for every $H$, this problem admits a…

Data Structures and Algorithms · Computer Science 2022-08-17 Łukasz Bożyk , Michał Pilipczuk

Kernels for structured data are commonly obtained by decomposing objects into their parts and adding up the similarities between all pairs of parts measured by a base kernel. Assignment kernels are based on an optimal bijection between the…

Machine Learning · Computer Science 2019-08-20 Nils M. Kriege

An independent vertex subset $S$ of the directed graph $G$ is a kernel if the set of out-neighbors of $S$ is $V(G)\setminus S$. An independent vertex subset $Q$ of $G$ is a quasi-kernel if the union of the first and second out-neighbors…

Combinatorics · Mathematics 2024-05-30 Péter L. Erdős , Ervin Győri , Tamás Róbert Mezei , Nika Salia , Mykhaylo Tyomkyn

Graph kernels based on the $1$-dimensional Weisfeiler-Leman algorithm and corresponding neural architectures recently emerged as powerful tools for (supervised) learning with graphs. However, due to the purely local nature of the…

Data Structures and Algorithms · Computer Science 2020-10-20 Christopher Morris , Gaurav Rattan , Petra Mutzel

Subgraph isomorphism counting is known as #P-complete and requires exponential time to find the accurate solution. Utilizing representation learning has been shown as a promising direction to represent substructures and approximate the…

Machine Learning · Computer Science 2024-05-14 Xin Liu , Weiqi Wang , Jiaxin Bai , Yangqiu Song

Let $H$ be a digraph possibly with loops and $D$ a digraph without loops with a coloring of its arcs $c:A(D) \rightarrow V(H)$ ($D$ is said to be an $H$-colored digraph). A directed path $W$ in $D$ is said to be an $H$-path if and only if…

Combinatorics · Mathematics 2020-06-09 Felipe Hernández-Lorenzana , Rocío Sánchez-López

We study the expansions of the elements in $\mathcal S(\mathbb{R}_+^d)$ and $\mathcal{S}'(\mathbb{R}_+^d)$ with respect to the Laguerre orthonormal basis, extending the result of M. Guillemont-Teissier in the case $d=1$. As a consequence,…

Functional Analysis · Mathematics 2016-02-15 Smiljana Jaksić , Bojan Prangoski

We introduce propagation kernels, a general graph-kernel framework for efficiently measuring the similarity of structured data. Propagation kernels are based on monitoring how information spreads through a set of given graphs. They leverage…

Machine Learning · Statistics 2014-10-14 Marion Neumann , Roman Garnett , Christian Bauckhage , Kristian Kersting