Results 81 to 90 of about 115,711 (260)

Manifold Regularization Graph Structure Auto-Encoder to Detect Loop Closure for Visual SLAM

open access: yesIEEE Access, 2019
Loop closure detection plays a vital role in the visual simultaneous localization and mapping (SLAM) systems. In order to overcome the shortcomings of the artificial design algorithm to extract insufficient features, this paper proposes a graph ...
Zhonghua Wang   +3 more
doaj   +1 more source

Deep Domain Adaptation Based on Adversarial Network With Graph Regularization

open access: yesIEEE Access, 2020
Although most transfer learning methods can reduce the difference of the feature distributions between the source and target domains effectively, some classes in the two domains may still be misaligned after domain adaptation, especially for the classes ...
Xu Jia, Na Ma, Fuming Sun
doaj   +1 more source

A partial refining of the Erdős-Kelly regulation [PDF]

open access: yesOpuscula Mathematica, 2019
The aim of this note is to advance the refining of the Erdős-Kelly result on graphical inducing regularization. The operation of inducing regulation (on graphs or multigraphs) with prescribed maximum vertex degree is originated by D. König in 1916. As is
Joanna Górska, Zdzisław Skupień
doaj   +1 more source

Generating r-regular graphs

open access: yesDiscrete Applied Mathematics, 2003
The authors study the problem of \(r\)-regular graph generation. The considered graphs can posses multiple edges between each pair \((x,y)\) of vertices, so they can be seen as labeled graphs with an integer accompanying each edge. Therefore, the subjective loopless graphs can be seen as flow networks. Two general approaches to generation are discussed.
Ding, Guoli, Chen, Peter
openaire   +2 more sources

Spectral Decomposition of Chemical Semantics for Activity Cliffs‐Aware Molecular Property Prediction

open access: yesAdvanced Science, EarlyView.
PrismNet mimics chemical intuition by functioning as a computational prism, refracting molecular graphs into complementary semantic views and spectral frequencies. This dual‐decomposition strategy effectively captures both global topologies and subtle “activity cliff” perturbations.
Chaoyang Xie   +9 more
wiley   +1 more source

Application of Non-Sparse Manifold Regularized Multiple Kernel Classifier

open access: yesMathematics
Non-sparse multiple kernel learning is efficient but not directly able to be applied in a semi-supervised scenario; therefore, we extend it to semi-supervised learning by using a manifold regularization.
Tao Yang
doaj   +1 more source

Multi‐View Biomedical Foundation Models for Molecule‐Target and Property Prediction

open access: yesAdvanced Science, EarlyView.
Molecular foundation models can provide accurate predictions for a large set of downstream tasks. We develop MMELON, an approach that integrates pre‐trained graph, image, and text foundation models and validate our multi‐view model on over 120 tasks, including GPCR binding.
Parthasarathy Suryanarayanan   +17 more
wiley   +1 more source

Approximately strongly regular graphs

open access: yesDiscrete Mathematics, 2023
We give variants of the Krein bound and the absolute bound for graphs with a spectrum similar to that of a strongly regular graph. In particular, we investigate what we call approximately strongly regular graphs. We apply our results to extremal problems. Among other things, we show the following: (1) Caps in $\mathrm{PG}(n, q)$ for which the number of
openaire   +3 more sources

On $k$-Walk-Regular Graphs [PDF]

open access: yesThe Electronic Journal of Combinatorics, 2009
Considering a connected graph $G$ with diameter $D$, we say that it is $k$-walk-regular, for a given integer $k$ $(0\leq k \leq D)$, if the number of walks of length $\ell$ between any pair of vertices only depends on the distance between them, provided that this distance does not exceed $k$. Thus, for $k=0$, this definition coincides with that of walk-
Dalfó Simó, Cristina   +2 more
openaire   +3 more sources

AI‐Based D‐Amino Acid Substitution for Optimizing Antimicrobial Peptides to Treat Multidrug‐Resistant Bacterial Infection

open access: yesAdvanced Science, EarlyView.
This study constructed the first D‐amino acid antimicrobial peptide dataset and developed an AI model for efficient screening of substitution sites, with 80% of candidate peptides showing enhanced activity. The lead peptide dR2‐1 demonstrated potent antimicrobial activity in vitro and in vivo, high stability, and low toxicity.
Yinuo Zhao   +14 more
wiley   +1 more source

Home - About - Disclaimer - Privacy