Results 1 to 10 of about 6,540,046 (323)
Atomistic Line Graph Neural Network for improved materials property predictions [PDF]
Npj Computational Materials, 2021 Graph neural networks (GNN) have been shown to provide substantial performance improvements for atomistic material representation and modeling compared with descriptor-based machine learning models.
K. Choudhary, Brian L. DeCost
semanticscholar +3 more sources
TransLiG: a de novo transcriptome assembler that uses line graph iteration. [PDF]
Genome Biol, 2019 We present TransLiG, a new de novo transcriptome assembler, which is able to integrate the sequence depth and pair-end information into the assembling procedure by phasing paths and iteratively constructing line graphs starting from splicing graphs ...
Liu J, Yu T, Mu Z, Li G.
europepmc +2 more sources
Graphs whose line graphs are ring graphs [PDF]
AKCE International Journal of Graphs and Combinatorics, 2020 Given a graph H, a path of length at least two is called an H-path if meets H exactly in its ends. A graph G is a ring graph if each block of G which is not a bridge or a vertex can be constructed inductively by starting from a single cycle and then in ...
Mahdi Reza Khorsandi
doaj +2 more sources
Modeling functional connectivity changes during an auditory language task using line graph neural networks [PDF]
Frontiers in Computational NeuroscienceFunctional connectivity (FC) refers to the activation correlation between different brain regions. FC networks as typically represented as graphs with brain regions of interest (ROIs) as nodes and functional correlation as edges.
Stein Acker +9 more
doaj +2 more sources
Line graphs of directed graphs I [PDF]
Transactions on CombinatoricsWe determine the forbidden induced subgraphs for the intersection of the classes of chordal bipartite graphs and line graphs of acyclic directed graphs. This is a first step towards finding the forbidden induced subgraphs for the class of line graphs of ...
Vaidyanathan Sivaraman, Daniel Slilaty
doaj +4 more sources
Lower bounds for on-line graph colorings
International Symposium on Algorithms and Computation, 2014 We propose two strategies for Presenter in on-line graph coloring games. The first one constructs bipartite graphs and forces any on-line coloring algorithm to use $2\log_2 n - 10$ colors, where $n$ is the number of vertices in the constructed graph ...
AA Diwan +8 more
core +2 more sources
LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations [PDF]
Annual Meeting of the Association for Computational Linguistics, 2021 This work aims to tackle the challenging heterogeneous graph encoding problem in the text-to-SQL task. Previous methods are typically node-centric and merely utilize different weight matrices to parameterize edge types, which 1) ignore the rich semantics
Ruisheng Cao +5 more
semanticscholar +1 more source
Line Graph Neural Networks for Link Weight Prediction [PDF]
Physica A: Statistical Mechanics and its Applications, 2023 In real-world networks, predicting the weight (strength) of links is as crucial as predicting the existence of the links themselves. Previous studies have primarily used shallow graph features for link weight prediction, limiting the prediction ...
Jinbi Liang, Cunlai Pu
semanticscholar +1 more source
Line Graph Contrastive Learning for Link Prediction [PDF]
Pattern Recognition, 2022 Link prediction tasks focus on predicting possible future connections. Most existing researches measure the likelihood of links by different similarity scores on node pairs and predict links between nodes.
Zehua Zhang +3 more
semanticscholar +1 more source
Orbital design of flat bands in non-line-graph lattices via line-graph wave functions [PDF]
Physical review B, 2021 Line-graph (LG) lattices are known for having flat bands (FBs) from the destructive interference of Bloch wavefunctions encoded in pure lattice symmetry.
Hang Liu +3 more
semanticscholar +1 more source