Improving Degree-Based Hashing (DBH) Graph Partitioning with a Novel Metric and Techniques
The paper introduces a novel metric called Maximal Sum of Inner Degrees Squared (MSIDS) and proposes an improved graph partitioning algorithm called DBH-X that balances the replication factor and MSIDS, leading to better performance for distributed graph processing algorithms.
Cuttana: A Scalable and High-Quality Graph Partitioning Approach for Faster Distributed Graph Processing
Cuttana is a two-phase graph partitioning algorithm that combines a prioritized buffered streaming model with a coarsening and refinement technique to produce high-quality partitions that outperform existing streaming partitioners, while maintaining scalability to massive graphs.
Leveraging Large Language Models for Uncertainty-Aware Graph Processing: Boosting Performance on Few-Shot Knowledge Graph Completion and Graph Classification
Large language models (LLMs) can be effectively harnessed for graph processing tasks, outperforming state-of-the-art algorithms across diverse benchmarks. An uncertainty-aware module is introduced to provide confidence scores on the generated answers, enhancing the explainability of the LLM-based approach.
© 2024 by Linnk AI