Results 21 to 30 of about 8,152,507 (265)
TransGNN: Harnessing the Collaborative Power of Transformers and Graph Neural Networks for Recommender Systems [PDF]
Graph Neural Networks (GNNs) have emerged as promising solutions for collaborative filtering (CF) through the modeling of user-item interaction graphs.
Peiyan Zhang +6 more
semanticscholar +1 more source
The expressive power of pooling in Graph Neural Networks [PDF]
In Graph Neural Networks (GNNs), hierarchical pooling operators generate local summaries of the data by coarsening the graph structure and the vertex features.
F. Bianchi, Veronica Lachi
semanticscholar +1 more source
The Expressive Power of Graph Neural Networks: A Survey [PDF]
Graph neural networks (GNNs) are effective machine learning models for many graph-related applications. Despite their empirical success, many research efforts focus on the theoretical limitations of GNNs, i.e., the GNNs expressive power.
Bingxue Zhang +6 more
semanticscholar +1 more source
Graph Powers and Graph Homomorphisms [PDF]
In this paper, we investigate some basic properties of fractional powers. In this regard, we show that for any non-bipartite graph $G$ and positive rational numbers ${2r+1\over 2s+1} < {2p+1\over 2q+1}$, we have $G^{2r+1\over 2s+1} < G^{2p+1\over 2q+1}$. Next, we study the power thickness of $G$, that is, the supremum of rational numbers ${2r+
Hajiabolhassan, Hossein, Taherkhani, Ali
openaire +3 more sources
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition [PDF]
Dynamics of human body skeletons convey significant information for human action recognition. Conventional approaches for modeling skeletons usually rely on hand-crafted parts or traversal rules, thus resulting in limited expressive power and ...
Sijie Yan, Yuanjun Xiong, Dahua Lin
semanticscholar +1 more source
SOME GRAPH PARAMETERS OF POWER SET GRAPHS
In this study, we examine some graph parameters such as the edge number, chromatic number, girth, domination number and clique number of power set graphs.
Cangül, İsmail Naci +3 more
openaire +2 more sources
Subsampling for graph power spectrum estimation [PDF]
In this paper we focus on subsampling stationary random signals that reside on the vertices of undirected graphs. Second-order stationary graph signals are obtained by filtering white noise and they admit a well-defined power spectrum.
S. Chepuri, G. Leus
semanticscholar +1 more source
Spanning connectedness and Hamiltonian thickness of graphs and interval graphs [PDF]
A spanning connectedness property is one which involves the robust existence of a spanning subgraph which is of some special form, say a Hamiltonian cycle in which a sequence of vertices appear in an arbitrarily given ordering, or a Hamiltonian path in ...
Peng Li, Yaokun Wu
doaj +1 more source
Chain graph reduction into power chain graphs
Reduction of graphs is a class of procedures used to decrease the dimensionality of a given graph in which the properties of the reduced graph are to be induced from the properties of the larger original graph. This paper introduces both a new method for reducing chain graphs to simpler directed acyclic graphs (DAGs), that we call power chain graphs ...
Víthor Rosa Franco +3 more
openaire +3 more sources
Forbidden Subgraphs of Power Graphs [PDF]
The undirected power graph (or simply power graph) of a group $G$, denoted by $P(G)$, is a graph whose vertices are the elements of the group $G$, in which two vertices $u$ and $v$ are connected by an edge between if and only if either $u=v^i$ or $v=u^j$ for some $i$, $j$.
Manna, Pallabi +2 more
openaire +5 more sources

