Results 41 to 50 of about 3,672,970 (235)
Characterizations of line graphs in signed and gain graphs [PDF]
European Journal of Combinatorics, 2022 We generalize three classical characterizations of line graphs to line graphs of signed and gain graphs: the Krausz's characterization, the van Rooij and Wilf's characterization and the Beineke's characterization. In particular, we present a list of forbidden gain subgraphs characterizing the class of gain-line graphs.
Daniele D'Angeli +2 more
openaire +3 more sources
Rethinking the Expressive Power of GNNs via Graph Biconnectivity [PDF]
International Conference on Learning Representations, 2023 Designing expressive Graph Neural Networks (GNNs) is a central topic in learning graph-structured data. While numerous approaches have been proposed to improve GNNs in terms of the Weisfeiler-Lehman (WL) test, generally there is still a lack of deep ...
Bohang Zhang +3 more
semanticscholar +1 more source
Freeness of hyperplane arrangements associated with gain graphs [PDF]
Athanasiadis studied arrangements obtained by adding shifted hyperplanes to the braid arrangement. Similarly, Bailey studied arrangements obtained by adding tilted hyperplanes to the braid arrangement. These two kinds of arrangements are associated with directed graphs and their freeness was characterized in terms of the associated graphs. In addition,
Suyama, Daisuke +2 more
openaire +3 more sources
Deep Graph Representation Learning and Optimization for Influence Maximization [PDF]
International Conference on Machine Learning, 2023 Influence maximization (IM) is formulated as selecting a set of initial users from a social network to maximize the expected number of influenced users. Researchers have made great progress in designing various traditional methods, and their theoretical ...
Chen Ling +7 more
semanticscholar +1 more source
GAIN: Graph Attention & Interaction Network for Inductive Semi-Supervised Learning Over Large-Scale Graphs [PDF]
IEEE Transactions on Knowledge and Data Engineering, 2020 Graph Neural Networks (GNNs) have led to state-of-the-art performance on a variety of machine learning tasks such as recommendation, node classification and link prediction.
Yunpeng Weng +3 more
semanticscholar +1 more source
SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models [PDF]
Annual Meeting of the Association for Computational Linguistics, 2022 Knowledge graph completion (KGC) aims to reason over known facts and infer the missing links. Text-based methods such as KGBERT (Yao et al., 2019) learn entity representations from natural language descriptions, and have the potential for inductive KGC ...
Liang Wang +3 more
semanticscholar +1 more source
The Electronic Journal of Linear Algebra, 2023 Let $\Phi=(G,U(\mathbb{Q}),\varphi)$ be a quaternion unit gain graph (or $U(\mathbb{Q})$-gain graph), where $G$ is the underlying graph of $\Phi$, $U(\mathbb{Q})=\{z\in \mathbb{Q}: |z|=1\}$ is the circle group, and $\varphi:\overrightarrow{E}\rightarrow ...
Qiannan Zhou, Yong Lu
semanticscholar +1 more source
Taming Local Effects in Graph-based Spatiotemporal Forecasting [PDF]
Neural Information Processing Systems, 2023 Spatiotemporal graph neural networks have shown to be effective in time series forecasting applications, achieving better performance than standard univariate predictors in several settings.
Andrea Cini +3 more
semanticscholar +1 more source
Matroids of Gain Signed Graphs
Discrete & Computational Geometry, 2023 13 fig., 46 pp. v2 has new Example 3.7, minor editing, 47 pp.
Laura Anderson +2 more
openaire +2 more sources
Burnside Chromatic Polynomials of Group-Invariant Graphs
Discussiones Mathematicae Graph Theory, 2023 We introduce the Burnside chromatic polynomial of a graph that is invariant under a group action. This is a generalization of the Q-chromatic function Zaslavsky introduced for gain graphs.
White Jacob A.
doaj +1 more source