Graph

Discover maximal balanced quasi-clique enumeration for signed graphs. A novel NP-hard algorithm identifies cohesive subgraphs with positive and negative edges using branch-and-bound optimization.

Framework for testing conditional and unconditional independence between binary graphs using community correlations and graph encoder embeddings.

Thoth hardware prefetcher improves performance on sparse data structures by tracking producer-consumer load pairs and using annotation-directed sampling to capture complex memory access patterns.

Graph neural network framework for assessing flood vulnerability in river basins. Identifies high-risk segments and flood-prone sub-basins by combining hydrological attributes with network topology.

DTMiner optimizes temporal motif mining by coordinating multiple matching tasks around shared data access patterns, achieving 1.14×-11.98× performance improvements.

Survey of graph-based techniques in retrieval-augmented generation systems, examining their roles in database construction, algorithms, and reasoning with structured knowledge.

Study proposes learnable communication graphs for multi-agent systems, enabling dynamic information sharing that adapts to task demands and reduces computational resource consumption.

Parallel algorithms for conflict graph management in mixed-integer programming enable larger cutting plane pools and substantially reduce solver times, especially for difficult problem instances.

Computational models of cognitive stages show that network-stage architectures outperform linear stages through estimation efficiency and explicit exposure tracking, not just parameter reduction.

CORE applies Information Bottleneck principles to augment graph data for link prediction, simultaneously recovering missing edges and reducing noise to enhance model robustness.

Automated pipeline for converting Excel spreadsheets to dynamic, publication-quality visualizations using machine learning chart recommendation and interactive dashboard functionality.

Systematic study of query optimization bugs in graph databases reveals root causes, manifestation patterns, and fixes to improve GDBMS reliability and system design.

Methodology for optimizing automated guided vehicle routes in hospitals using BIM, IFC standards, and graph-based pathfinding algorithms to enhance logistics efficiency.

BenchPCNP: A labeled printed circuit netlist graph dataset for partitioning benchmarking, constructed from 50 production-verified circuits with 54 distinct module labels following IPC-2612 standards.

Prompt-driven framework combining LLMs with knowledge graphs for reliable knowledge-based question answering through structured subgraph retrieval and stepwise reasoning validation.

Graph matching framework for cross-modality intravascular ultrasound and optical coherence tomography sequence registration with simultaneous temporal and rotational alignment.

Graph neural networks with augmented brain signals improve MDD diagnosis through gender-specific and stage-wise analysis, enabling personalized therapeutic strategies.

Learn how retrieval augmentation and structural priors enhance parameter-efficient code representations while using only 5% of standard fine-tuning parameters.