Weekly graph technology trend reviews covering graph databases, GraphRAG, GNNs, ontology, and knowledge graphs.
GraphOmakase
Graph Interview 소식 Graph Interview - 10th - Tobias Rebert - · LumaDifferentiate from LPG: RDF’s Real PowerLPG 대비 RDF가 가지는 결정적인 차별점과, 추상적인 온톨로지를 실제 데이터 레이어에서 강력하게 구현해내는 RDF만의 파워 Great Modeling for RDF (Migration from Knowledge…Yitae Jeong * 오는 8월 25일(화) 오후 8시–10시, 저희 GUG에서 진행하는 Graph Interview
GraphOmakase
Is GraphRAG Needed? From Basic RAG to Graph-/Agentic Solutions with Context Optimization Is GraphRAG Needed? From Basic RAG to Graph-/Agentic Solutions with Context OptimizationLong Chen, Ryan Razkenari, Yuxuan Zhou, Yuan Tian, Rahul Ghosh, Venkatesh Pappakrishnan, Disha Ahuja, Vidya Sagar Ravipati. Proceedings of the Fifth Workshop on Generation, Evaluation
GraphOmakase
Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with GraphsLarge language models (LLMs) often struggle with knowledge-intensive tasks due to hallucinations and outdated parametric knowledge. While Retrieval-Augmented Generation (RAG) addresses
GraphOmakase
GUG 커뮤니티의 반가운 소식 * 오랜만에 인사드립니다 ! 다시 오마카세를 찾아주신 분들도, 이번에 처음 오신 분들도 모두 반갑습니다. 한국도 무더위가 이어지고 있다고 들었는데, 모두 건강하게 잘 지내고 계셨나요? * 최근 저희 GUG(Graph User Group)에 정말 반가운 소식이 있어서 전해드리고자 합니다. GUG가 2026 오픈소스 AI·SW 커뮤니티 지원사업에 선정되었습니다. 7월 25일(토요일)
GraphOmakase
Topological Neural Operator Topological Neural OperatorsWe introduce Topological Neural Operators (TNOs), a principled framework for operator learning on cell complexes that lifts neural operators (NOs) from functions on points and/or edges to topological domains. TNOs represent data as features defined on cells of varying dimension and model their interactions
GraphOmakase
AI Must Embrace Specialization via Superhuman Adaptable Intelligence AI Must Embrace Specialization via Superhuman Adaptable IntelligenceEveryone from AI executives and researchers to doomsayers, politicians, and activists is talking about Artificial General Intelligence (AGI). Yet, they often don’t seem to agree on its exact definition. One common definition of AGI
GraphOmakase
Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node ClassificationarXiv logoGitHub - transductive-sharpening/tunedGNN: Transductive Sharpening applied on top of the TunedGNN baseline.Transductive Sharpening applied on top of the TunedGNN baseline. - transductive-sharpening/tunedGNNGitHubtransductive-sharpening Keywords * Transductive Learning * Semi-supervised GNN
GraphOmakase
Learning Higher-Order Structure from Incomplete Spatiotemporal Data: Multi-Scale Hypergraph Laplacians with Neural Refinement Learning Higher-Order Structure from Incomplete Spatiotemporal Data: Multi-Scale Hypergraph Laplacians with Neural RefinementSensor networks increasingly govern modern infrastructure, yet the data they lose are rarely missing in the uniform-random patterns assumed by
GraphOmakase
Random Sets Graph Neural Networks Random-Set Graph Neural NetworksUncertainty quantification has become an important factor in understanding the data representations produced by Graph Neural Networks (GNNs). Despite their predictive capabilities being ever useful across industrial workspaces, the inherent uncertainty induced by the nature of the data is a huge
GraphOmakase
Root-to-Leaf Path Random Walks, Normalized Hodge Laplacians, and Cheeger Inequalities on Simplicial Complexes Root-to-Leaf Path Random Walks, Normalized Hodge Laplacians, and Cheeger Inequalities on Simplicial ComplexesWe introduce root-to-leaf path random walks on double covers of graded signed graphs and analyze their behavior in a
GraphOmakase
Deep GraphRAG: A Balanced Approach to Hierarchical Retrieval and Adaptive Integration Deep GraphRAG: A Balanced Approach to Hierarchical Retrieval and Adaptive IntegrationGraph-based Retrieval-Augmented Generation (GraphRAG) frameworks face a trade-off between the comprehensiveness of global search and the efficiency of local search. Existing methods are often challenged by
GraphOmakase
Topology-Aware Representation Alignment for Semi-Supervised Vision-Language Learning Topology-Aware Representation Alignment for Semi-Supervised Vision-Language LearningVision-language models have shown strong performance, but they often generalize poorly to specialized domains. While semi-supervised vision-language learning mitigates this limitation by leveraging a small set of labeled