Tag
This paper proposes a Multi-Granularity Hypergraph Representation Learning (MGHRL) framework that adaptively generates hyperedges at multiple granularities using granular-ball splitting to capture high-order relationships in graphs, outperforming baseline models on benchmark datasets.
SemHash-LLM is a multi-granularity semantic hashing framework that combines projection hashing, attention-weighted MinHash, contrastive learning, and selective LLM adjudication for efficient and robust large-scale document deduplication.
Proposes a Multi-Granularity Reasoning Network (MGRN) that explicitly leverages hierarchical semantic features for natural language inference, outperforming strong baselines on multiple benchmarks.