Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 10,000 papers for “graph representation”

Graph Representation

Alfred V. Aho, Mark S. Goldberg, Josef Lauri et al. · Discrete mathematics and its applications · 2003

Cited by 0

Graph Representation Learning

Peng Cui, Lingfei Wu, Jian Pei et al. · 2022

Cited by 13

Graph Representation Learning

Wei Jin, Yao Ma, Yiqi Wang et al. · 2021

Graphs such as social networks and molecular graphs are ubiquitous data structures in the real world. Due to their prevalence, it is of great research importance to extract meaningful patterns from graph structured data so that downstream tasks can be facilitated. Instead of designing hand-engineered features, graph representation learning has emerged to learn representations that can encode the abundant information about the graph. It has achieved tremendous success in various tasks such as node classification, link prediction, and graph classification and has attracted increasing attention in recent years.

Cited by 130

Flow graph representation

Alex Orailoğlu, Daniel D. Gajski · Proceedings of the 23rd ACM/IEEE conference on Design automation - DAC '86 · 1986

Cited by 12

Graph Representation Learning

Cheng Yang, Yankai Lin, Zhiyuan Liu et al. · 2023

Abstract Graph structure, which can represent objects and their relationships, is ubiquitous in big data including natural languages. Besides original text as a sequence of word tokens, massive additional information in NLP is in the graph structure, such as syntactic relations between words in a sentence, hyperlink relations between documents, and semantic relations between entities. Hence, it is critical for NLP to encode these graph data with graph representation learning. Graph representation learning, also known as network embedding, has been extensively studied in AI and data mining. In this chapter, we introduce a variety of graph representation learning methods that embed graph data into vectors with shallow or deep neural models. After that, we introduce how graph representation learning helps NLP tasks.

Cited by 3Open access

Reduced graph representation.

Markus Hartenfeller (185082), Heiko Zettl (185086), Miriam Walter (185090) et al. · Figshare · 2015

(A) An example of a reduced graph representation. Dashed lines connect atoms or rings of the molecule (left) with their corresponding vertex of the reduced graph (right). For clarity only some lines are shown. (B) Examples of polycyclic (‘amalgamated’) substructures translated to a single vertex in the reduced graph. (C) Edges of order two are used to connect fused rings (bottom) in order to distinguish the shown cases of neighbored rings in reduced graph representation.

Cited by 0Open access

Graphics Graph Representation

Matula, Radek · Brno University of Technology Digital Library (Brno University of Technology) · 2009

Tato diplomová práce se zabývá zobrazovacími algoritmy grafů známých z matematické teorie. Tyto algoritmy řeší problematiku vhodného rozmístění uzlů grafu tak, aby byl výsledný graf co nejvíce přehledný a čitelný člověkem. Hlavním cílem práce bylo také implementovat vlastní zobrazovací algoritmus v aplikaci, která by umožňovala graf editovat. Práce se také zabývá problematikou reprezentace grafů v počítačích.

Cited by 0

Factor graph representation.

Fabrizio Altarelli (770492), Alfredo Braunstein (52117), Luca Dall’Asta (770493) · Figshare · 2015

Left: For the deterministic case the set of constraints is <mo>C</mo><mo>(</mo><mi>y</mi><mo>)</mo><mo>=</mo><mo>∏</mo><mi>u</mi><mo>∈</mo><mi>U</mi><mi>ψ</mi><mi>u</mi><mo>(</mo><mi>y</mi><mi>u</mi><mo>)</mo><mo>∏</mo><mi>a</mi><mo>∈</mo><mi>S</mi><mi>ϕ</mi><mi>a</mi><mo>(</mo><mi>y</mi><mi>a</mi><mo>)</mo>. Right: For the stochastic case, the factor graph includes mirror nodes (black lozanges) and the corresponing messages Qu(tu). The set of constraints is <mo>C</mo><mo>(</mo><mi>y</mi><mo>,</mo><mi>t</mi><mo>)</mo><mo>=</mo><mo>∏</mo><mi>u</mi><mo>∈</mo><mi>U</mi><mi>ψ</mi><mi>u</mi><mo>(</mo><mi>y</mi><mi>u</mi><mo>,</mo><mi>t</mi><mi>u</mi><mo>)</mo><mo>∏</mo><mi>a</mi><mo>∈</mo><mi>S</mi><mi>ϕ</mi><mi>a</mi><mo>(</mo><mi>y</mi><mi>a</mi><mo>)</mo>.

Cited by 0Open access

Graph signal representation.

Tamanna Tabassum Khan Munia (4019771), Selin Aviyente (7300028) · Figshare · 2019

The first six signals obtained from graph-to-signal transformation of a. CRN networks; b. ERN networks.

Cited by 0Open access

Graph Representation Learning

Davide Bacciu, Federico Errica, Alessio Micheli et al. · 2023

In a broad range of real-world machine learning applications, representing examples as graphs is crucial to avoid a loss of information.For this reason, in the last few years, the definition of machine learning methods, particularly neural networks, for graph-structured inputs has been gaining increasing attention.In particular, Deep Graph Networks (DGNs) are nowadays the most commonly adopted models to learn a representation that can be used to address different tasks related to nodes, edges, or even entire graphs.This tutorial paper reviews fundamental concepts and open challenges of graph representation learning and summarizes the contributions that have been accepted for publication to the ESANN 2023 special session on the topic.

Cited by 3Open access

Graph representation learning

Xinyi Zhang · 2022

encouraged me to start my Ph.D study in

Cited by 1Open access

Coherence graph representation.

Inon Zuckerman (8399517), Dor Mizrahi (8399514), Ilan Laufer (346696) · Figshare · 2023

Cited by 0Open access

494 Graph representation

Aiman Gannous · 2025

Cited by 0

Configurable hyperdimensional graph representation

Ali Zakeri, Zhuowen Zou, Hanning Chen et al. · Artificial Intelligence · 2025

Graph analysis has emerged as a crucial field, offering versatile solutions for real-world data representation, from social networks to biological systems. However, the intricate nature of graphs often necessitates a degree of processing, such as learning mappings to a vector space, to perform analysis tasks like node classification and link prediction. A promising approach to this is Hyperdimensional Computing (HDC), inspired by neuroscience and mathematics. HDC utilizes high-dimensional vectors to efficiently manipulate complex data structures and perform operations like superposition and association, enhancing knowledge graph representations with contextual and semantic information. Nevertheless, addressing limitations in existing HDC-based approaches to graph representation is essential. This paper thoroughly explores these methods and presents ConfiGR: Configurable Graph Representation, a novel framework that introduces an adjustable design, enhancing its versatility across various graph types and tasks, ultimately boosting performance in multiple graph-related tasks.

Cited by 0Open access

Components of graph representation.

Hoyeon Jeong (18264791), Young-Rae Cho (87587), Jungsoo Gim (449119) et al. · Figshare · 2024

<div>Neoantigens are tumor-derived peptides and are biomarkers that can predict prognosis related to immune checkpoint inhibition by estimating their binding to major histocompatibility complex (MHC) proteins. Although deep neural networks have been primarily used for these prediction models, it is difficult to interpret the models reported thus far as accurately representing the interactions between biomolecules. In this study, we propose the GraphMHC model, which utilizes a graph neural network model applied to molecular structure to simulate the binding between MHC proteins and peptide sequences. Amino acid sequences sourced from the immune epitope database (IEDB) undergo conversion into molecular structures. Subsequently, atomic intrinsic informations and inter-atomic connections are extracted and structured as a graph representation. Stacked graph attention and convolution layers comprise the GraphMHC network which classifies bindings. The prediction results from the test set using the GraphMHC model showed a high performance with an area under the receiver operating characteristic curve of 92.2% (91.9-92.5%), surpassing a baseline model. Moreover, by applying the GraphMHC model to melanoma patient data from The Cancer Genome Atlas project, we found a borderline difference (0.061) in overall survival and a significant difference in stromal score between the high and low neoantigen load groups. This distinction was not present in the baseline model. This study presents the first feature-intrinsic method based on biochemical molecular structure for modeling the binding between MHC protein sequences and neoantigen candidate peptide sequences. This model can provide highly accurate responsibility information that can predict the prognosis of immune checkpoint inhibitors to cancer patients who want to apply it.</div>

Cited by 0Open access

Spatial-temporal graph representation.

Libiao Chen (15187963), Qiang Ren (1565044), Juncheng Zeng (15187966) et al. · Figshare · 2023

Cited by 0Open access

Asymmetric Graph Representation Learning

Zhuo Tan, Bin Liu, Guosheng Yin · arXiv (Cornell University) · 2021

Despite the enormous success of graph neural networks (GNNs), most existing GNNs can only be applicable to undirected graphs where relationships among connected nodes are two-way symmetric (i.e., information can be passed back and forth). However, there is a vast amount of applications where the information flow is asymmetric, leading to directed graphs where information can only be passed in one direction. For example, a directed edge indicates that the information can only be conveyed forwardly from the start node to the end node, but not backwardly. To accommodate such an asymmetric structure of directed graphs within the framework of GNNs, we propose a simple yet remarkably effective framework for directed graph analysis to incorporate such one-way information passing. We define an incoming embedding and an outgoing embedding for each node to model its sending and receiving features respectively. We further develop two steps in our directed GNN model with the first one to aggregate/update the incoming features of nodes and the second one to aggregate/update the outgoing features. By imposing the two roles for each node, the likelihood of a directed edge can be calculated based on the outgoing embedding of the start node and the incoming embedding of the end node. The log-likelihood of all edges plays a natural role of regularization for the proposed model, which can alleviate the over-smoothing problem of the deep GNNs. Extensive experiments on multiple real-world directed graphs demonstrate outstanding performances of the proposed model in both node-level and graph-level tasks.

Cited by 2Open access

Signed Graph Representation Learning

Zhang, Zeyu · ResearchSpace (University of Auckland) · 2023

This thesis considers the research on signed graph representation learning in different aspects. Signed graphs model complex relations using both positive and negative edges and signed graph neural networks (SGNNs) are powerful tools to analyze signed graphs. Our thesis mainly involves the research of SGNNs, trying to explore SGNN in terms of robustness, training schedule, and extension. Towards this goal, we perform following four tasks: (1) To comprehensively understand the research progress of signed graph representation learning and to the best of our knowledge there exists no related review in this area, we conduct a systematic survey on current methods which are classified into three main categories, i.e., matrix factorization based methods, random walk based methods and neural network based methods; (2) Robustness research is important in signed graph neural networks as graph neural networks (GNNs) have been proved to be vulnerable to noisy information. We address the vulnerability of SGNN to potential edge noise in the input graph and strengthen existing SGNN allowing them to withstand edge noises by extracting robust representations for signed graphs; (3) Contrastive learning has achieved great success in improving the robustness of graph representation learning. Although recent studies have introduced contrastive learning for signed graphs, no existing study has been conducted specifically on signed bipartite graphs, which widely exist in social networks, recommender systems, paper review platforms, etc. We are the first to exploit contrastive learning for signed bipartite graphs; (4) Existing methods for training SGNN usually feed edges (samples) to models in a random order so that the edges make equal contributions during training. However, the learning difficulty of samples varies greatly due to the graph structures, and we argue that SGNNs can benefit from an easy-to-difficult curriculum, similar to the learning process of humans. Thus, we propose a novel curriculum representation learning framework for signed graph.

Cited by 0Open access