Results 31 to 40 of about 2,422,838 (348)
Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling [PDF]
Conference on Empirical Methods in Natural Language Processing, 2017 Semantic role labeling (SRL) is the task of identifying the predicate-argument structure of a sentence. It is typically regarded as an important step in the standard NLP pipeline.
Diego Marcheggiani, Ivan Titov
semanticscholar +1 more source
A Dynamic Survey of Graph Labeling
Electronic Journal of Combinatorics, 2009 A graph labeling is an assignment of integers to the vertices or edges, or both, subject to certain conditions. Graph labelings were first introduced in the mid-1960s. In the intervening years over 200 graph labelings techniques have been studied in over
Joseph A. Gallian
semanticscholar +1 more source
Shifted-Antimagic Labelings for Graphs [PDF]
Graphs and Combinatorics, 2021 The concept of antimagic labelings of a graph is to produce distinct vertex sums by labeling edges through consecutive numbers starting from one. A long-standing conjecture is that every connected graph, except a single edge, is antimagic. Some graphs are known to be antimagic, but little has been known about sparse graphs, not even trees.
Fei-Huang Chang +3 more
openaire +4 more sources
Boletim da Sociedade Paranaense de Matemática, 2019 A graph labeling is an assignment of integers to the vertices, edges, or to both, and it is subject to certain conditions. In this paper, a new concept of graph labeling called binary operation labeling is introduced.
Manal Naji Al-Harere +1 more
doaj +1 more source
Odd Fibonacci Stolarsky-3 Mean Labeling of Some Special Graphs
Ratio Mathematica, 2022 Let G be a graph with p vertices and q edges and an injective function where each is a odd Fibonacci number and the induced edge labeling are defined by and all these edge labeling are distinct is called Odd Fibonacci Stolarsky-3 Mean Labeling.
M Sree Vidya, S.S Sandhya
doaj +1 more source
Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shift [PDF]
The Web Conference, 2022 Graph Convolutional Networks (GCNs) have recently attracted vast interest and achieved state-of-the-art performance on graphs, but its success could typically hinge on careful training with amounts of expensive and time-consuming labeled data.
Hongrui Liu +5 more
semanticscholar +1 more source
Discrete Mathematics, 1994 AbstractIn this note, we extend Schützenberger's evacuation of Young tableaux (Schützenberger, 1963), and naturally labelled posets (Schützenberger, 1972), to labelled graphs. It is shown that evacuation is an involution, and that in that in the dual evacuation, tracks and trajectories are interchanged.
MALVENUTO, Claudia, REUTENAUER C.
openaire +2 more sources
Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning [PDF]
International Joint Conference on Artificial Intelligence, 2021 Graph representation learning plays a vital role in processing graph-structured data. However, prior arts on graph representation learning heavily rely on labeling information. To overcome this problem, inspired by the recent success of graph contrastive
Ming Jin +5 more
semanticscholar +1 more source
On the study of Rainbow Antimagic Coloring of Special Graphs
Cauchy: Jurnal Matematika Murni dan Aplikasi, 2023 Let be a connected graph with vertex set and edge set . The bijective function is said to be a labeling of graph where is the associated weight for edge .
Dafik Dafik +3 more
doaj +1 more source
A Note on 1-Edge Balance Index Set [PDF]
, 2012 A graph labeling is an assignment of integers to the vertices or edges or both, subject to certain conditions. Varieties of graph labeling have been investigated by many authors [2], [3] [5] and they serve as useful models for broad range of ...
Chandrashekar Adiga, +2 more
core +1 more source