Research & Literature | Graph Technology Institute
{
"@context": "https://schema.org",
"@type": "CollectionPage",
"name": "Research — Graph Technology Institute",
"description": "Curated research papers in graph AI, knowledge graphs, graph databases, and network analysis from arXiv.",
"about": {
"@type": "Thing",
"name": "Graph Technologies Research"
}
}
Skip to main contentGTIGraph Technology InstituteAboutGraph of GraphsResearchEventsGet Involved
Data & KnowledgeAI & MLSocial & NetworkInfrastructureScience & ResearchSemantic WebData & Knowledge9 papers2510.20345 2025LLM-empowered Knowledge Graph Construction: A SurveySystematic analysis of how LLMs reshape the three-layered KG construction pipeline — ontology engineering, knowledge extraction, and knowledge fusion.GTI Relevance: Demonstrates the convergence of LLMs and knowledge graphs, a central topic for educating practitioners on modern KG construction.2501.13958 2025A Survey of Graph Retrieval-Augmented Generation for Customized LLMsIntroduces GraphRAG as a paradigm overcoming traditional RAG limitations through graph-structured knowledge representation, enabling multihop reasoning.GTI Relevance: GraphRAG is a breakthrough application of knowledge graphs in AI systems, ideal for practical KG education.2512.16487 2025A Survey on Spatio-Temporal Knowledge Graph ModelsSurveys STKGs that integrate entities, relationships, time, and space for environmental systems, urban planning, and transportation.GTI Relevance: Demonstrates how knowledge graphs extend beyond static representations into temporal and spatial domains.2505.24758 2025Survey: Graph DatabasesComprehensive survey examining property graph models, query languages (Cypher, PGQL, GQL), and storage architectures.GTI Relevance: Essential reference covering the full landscape of graph database technologies and standards.2511.08274 2025Multi-Agent GraphRAG: Text-to-Cypher for Labeled Property GraphsMulti-agent framework translating natural language questions into Cypher queries over labeled property graphs.GTI Relevance: Bridges natural language AI and property graph databases, demonstrating practical interoperability.2511.23388 2025Learning-Augmented Online Bipartite MatchingAdvances algorithmic theory for bipartite graph optimization with ML-augmented decision-making in the random arrival model.GTI Relevance: Demonstrates the intersection of classical graph algorithms and modern ML for bipartite applications.2402.10409 2024Understanding Survey Paper Taxonomy via Graph Representation LearningUses graph representation learning on co-category structures to classify papers within a taxonomy, outperforming language models.GTI Relevance: Shows how graph methods organize knowledge hierarchically, relevant to taxonomy graph education.2403.00165 2024TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text ClassificationCombines LLMs with taxonomy enrichment for hierarchical text classification using graph-structured label hierarchies.GTI Relevance: Illustrates how taxonomy graphs are enriched and leveraged in modern NLP pipelines.2507.13859 2025SPARQL Query Generation with LLMs: Training Data Memorization & Knowledge InjectionEvaluates LLM-generated SPARQL queries for question answering over knowledge graphs and linked data endpoints.GTI Relevance: Shows how modern AI interfaces with SPARQL and RDF endpoints for linked data querying.AI & Machine Learning8 papers2403.04468 2024GNNs in the Real World: Imbalance, Noise, Privacy and OOD ChallengesReviews GNN solutions to four critical real-world challenges: class imbalance, noisy data, privacy constraints, and out-of-distribution generalization.GTI Relevance: Essential survey for understanding practical GNN deployment challenges.2412.20634 2024Graph Neural Networks for Next-Generation IoTExplores GNN deployment in next-gen IoT systems with 6G technologies — massive MIMO, RIS, THz communication, and satellite systems.GTI Relevance: Shows the expanding frontier of GNN applications beyond traditional domains.2406.05027 2024Optimizing Automatic Differentiation with Deep Reinforcement LearningFrames automatic differentiation as an ordered vertex elimination problem on the computational graph, using deep RL for efficient elimination.GTI Relevance: Directly addresses computational graph optimization for neural network training.2504.08277 2025Enabling Automatic Differentiation with Mollified Graph Neural OperatorsFirst method to leverage automatic differentiation and compute exact gradients on arbitrary geometries via graph neural operators.GTI Relevance: Extends computational graph concepts into scientific computing via graph neural operators.2503.17025 2025Bayesian Network Software Packages: Structure & Parameter Learning (2025 Ed.)Reviews the most relevant tools for Bayesian Network structure and parameter learning with practical recommendations.GTI Relevance: Directly useful as an educational resource for Bayesian network tooling.2511.00574 2025Bayesian Network Structure Discovery Using Large Language ModelsUnified framework (PromptBN and ReActBN) placing LLMs at the center of Bayesian network structure discovery.GTI Relevance: New paradigm for Bayesian network construction using LLMs, transforming classical graph methods.2505.03229 2025Survey of Abstract Meaning Representation: Then, Now, FutureComprehensive survey of AMR parsing (text-to-AMR) and generation (AMR-to-text), with applications in NLP tasks.GTI Relevance: Definitive reference for NLP graph curriculum covering the full AMR landscape.2508.05028 2025Finetuned LLMs in Abstract Meaning Representation ParsingDemonstrates that finetuning decoder-only LLMs achieves comparable performance to complex AMR parsers, simplifying graph construction.GTI Relevance: LLMs are democratizing AMR graph parsing, lowering barriers to entry.Social & Network7 papers2309.11798 2024A Comprehensive Review of Community Detection in GraphsThorough exposition of community detection methods: modularity-based, spectral clustering, probabilistic modeling, and deep learning.GTI Relevance: Comprehensive reference covering the full spectrum of community detection methods.2509.24662 2025Community Detection Robustness of Graph Neural NetworksEvaluates robustness of GNN-based community detection under adversarial perturbations and noisy graph structures.GTI Relevance: Can GNN-based community detection be trusted in real-world social networks?2411.05815 2024Graph Neural Networks for Financial Fraud Detection: A ReviewUnified framework categorizing GNN methodologies for financial fraud detection, significantly outperforming traditional methods.GTI Relevance: Core reference demonstrating graph technology's high-impact application in fraud prevention.2508.20829 2025ATM-GAD: Adaptive Temporal Motif Graph Anomaly DetectionTemporal motif extraction and dual-attention blocks detect multi-step fraud schemes in financial networks.GTI Relevance: Breakthrough in temporal financial graph analysis using graph motifs.2511.00047 2025DynBERG: Dynamic BERT-based GNN for Financial Fraud DetectionIntegrates Graph-BERT with GRU layers to capture temporal evolution across subgraphs in directed financial transaction networks.GTI Relevance: Shows the convergence of transformer and graph architectures for temporal financial networks.2502.17928 2025Structure-prior Informed Diffusion Model for Graph Source LocalizationGenerative diffusion framework with topology-aware priors for robust source localization in information propagation networks.GTI Relevance: Addresses tracing misinformation origins, cyber threats, and infrastructure failures in networks.2502.13571 2025Diffusion Model Agnostic Social Influence Maximization in Hyperbolic SpaceInfluence maximization methods using hyperbolic space representations that capture hierarchical social influence structures.GTI Relevance: Novel geometric perspective on influence propagation graphs, expanding the mathematical toolkit.Infrastructure5 papers2505.12355 2025GATES: Cost-aware Dynamic Workflow Scheduling via GATs and Evolution StrategyCloud workflow scheduling where DAG tasks are assigned to VMs using deep RL with graph attention networks learning topological relationships.GTI Relevance: Prime example of DAG structure leveraged by modern AI for infrastructure optimization.2503.22365 2025Memory-aware Adaptive Scheduling of Scientific Workflows on Heterogeneous ArchitecturesScientific workflows as DAGs achieving optimal makespan under memory constraints on heterogeneous processors.GTI Relevance: Classic DAG application in scientific computing for scheduling optimization.2406.09953 2024DAG-Plan: Generating DAGs for Dual-Arm Cooperative PlanningAutomatically generates directed acyclic dependency graphs for robotic task planning, enabling cooperative execution.GTI Relevance: Shows how dependency graphs enable AI-driven robotic planning.2411.08550 2024GNNs in Supply Chain Analytics: Concepts, Dataset and BenchmarksEstablishes supply chains as inherently graph-like, presents a multi-perspective real-world FMCG benchmark dataset.GTI Relevance: Foundational paper with real-world benchmark data ideal for educational use.2504.03692 2025Graph-based Digital Twins for Supply Chain Management and OptimizationCombines graph modeling with Digital Twin architecture for dynamic, real-time supply network representations.GTI Relevance: Cutting-edge graph technology application (digital twins) for supply chain research.Science & Research7 papers2509.00987 2025Causal MAS: LLM Architectures for Discovery and Effect EstimationSurveys multi-agent systems leveraging LLM agents for causal reasoning in scientific discovery, healthcare, and fact-checking.GTI Relevance: LLM agents used for causal graph discovery represent a new AI-driven paradigm.2402.11068 2024Large Language Models for Causal Discovery: Current Landscape & FutureExamines how LLMs transform causal discovery: direct extraction, domain knowledge integration, and structure refinement.GTI Relevance: Comprehensive overview of the LLM–causal graph intersection.2509.25800 2025Causal Graphs with Latent Confounders from Interventional DataAdvances interventional causal discovery by identifying causal relations through distributional changes, even with latent confounders.GTI Relevance: Pushes the theoretical frontier of causal graph learning.2509.07887 2025GNNs for Drug Discovery: Recent Developments and ChallengesComprehensive survey spanning molecular property prediction, virtual screening, molecular generation, and synthesis planning.GTI Relevance: Definitive reference for molecular graph applications in drug discovery.2502.08975 2025Graph-structured Small Molecule Drug Discovery Through Deep LearningReviews deep learning on graph-structured molecular representations for property prediction, de novo generation, and reaction prediction.GTI Relevance: Focused specifically on graph-structured molecular representations.2507.05101 2025PRING: Rethinking Protein-Protein Interaction Prediction from Pairs to GraphsFirst comprehensive benchmark evaluating PPI prediction from a graph-level perspective (21,484 proteins, 186,818 interactions).GTI Relevance: Landmark benchmark for protein interaction graph research.2501.17589 2025Extracting Inter-Protein Interactions Via Multitasking Graph Structure LearningGraph attention mining of protein structural information with multitask learning to advance PPI prediction accuracy.GTI Relevance: Graph structure learning directly enables biological discovery.Semantic Web4 papers2511.05991 2025Ontology Learning and Knowledge Graph Construction: A ComparisonCompares approaches to automated ontology learning, demonstrating how LLMs enable ontology extraction from structured and unstructured data.GTI Relevance: Bridges ontology engineering and modern AI, revitalizing semantic web technologies.2507.20643 2025Ontology-Enhanced Knowledge Graph Completion using LLMsDemonstrates how ontological information in RDF triples enhances knowledge graph completion through LLMs.GTI Relevance: Practical value of RDF ontologies for improving knowledge graph quality.2507.10045 2025Automating SPARQL Query Translations between DBpedia and WikidataEvaluates LLM performance on SPARQL-to-SPARQL translation between major linked data knowledge graphs.GTI Relevance: Tackles a key linked data challenge: interoperability between RDF knowledge graphs.2410.13948 2024The KnowWhereGraph OntologyLarge-scale geospatial knowledge graph built on RDF and linked data principles for environmental and humanitarian applications.GTI Relevance: Real-world deployment of semantic web technologies for societal benefit.GTIGraph Technology InstituteA tax-exempt educational intermediary promoting transparency, trust, and collaboration while ethically advancing graph technologies for business and society.InstituteAbout GTIHow We WorkGraph of GraphsResearchGovernanceCommunityEventsJoin ConsortiumContributePartnersLegalPrivacy PolicyTerms of ServiceAccessibilityContact Us© Graph Technology Institute. All rights reserved.501(c)(3) Tax-Exempt Organization 40);
}, { passive: true });
function toggleMobileMenu() {
var m = document.querySelector('.mobile-menu'), b = document.querySelector('.hamburger');
var o = m.classList.toggle('open');
b.classList.toggle('active', o); b.setAttribute('aria-expanded', o);
m.setAttribute('aria-hidden', !o); document.body.style.overflow = o ? 'hidden' : '';
}
function filterDomain(domain, btn) {
document.querySelectorAll('.domain-btn').forEach(function(b) { b.setAttribute('aria-pressed', 'false'); });
btn.setAttribute('aria-pressed', 'true');
document.querySelectorAll('.domain-section').forEach(function(s) {
if (domain === 'all' || s.getAttribute('data-domain') === domain) {
s.classList.remove('hidden');
} else {
s.classList.add('hidden');
}
});
}
(function() {
var obs = new IntersectionObserver(function(entries) {
entries.forEach(function(e) { if (e.isIntersecting) { e.target.classList.add('visible'); obs.unobserve(e.target); } });
}, { threshold: 0.05, rootMargin: '0px 0px -30px 0px' });
document.querySelectorAll('.reveal').forEach(function(el) { obs.observe(el); });
})();
' +
'' + m.label + '
' + m.text + '';
}).join('');
results.classList.toggle('has-results', matches.length > 0);
activeResult = -1;
});
document.querySelector('.search-input').addEventListener('keydown', function(e) {
var items = document.querySelectorAll('.search-result');
if (e.key === 'ArrowDown') { e.preventDefault(); activeResult = Math.min(activeResult + 1, items.length - 1); }
else if (e.key === 'ArrowUp') { e.preventDefault(); activeResult = Math.max(activeResult - 1, 0); }
else if (e.key === 'Enter' && activeResult >= 0) { items[activeResult].click(); return; }
items.forEach(function(el, i) { el.classList.toggle('active', i === activeResult); });
});
function goTo(el) { var href = el.getAttribute('data-href'); toggleSearch(); window.location.href = href; }
document.addEventListener('keydown', function(e) {
if ((e.ctrlKey || e.metaKey) && e.key === 'k') { e.preventDefault(); toggleSearch(); }
if (e.key === 'Escape') { var o = document.querySelector('.search-overlay'); if (o && o.classList.contains('open')) toggleSearch(); }
});
document.querySelector('.search-overlay').addEventListener('click', function(e) { if (e.target === this) toggleSearch(); });
/script>