← Back to all news
arXiv Machine Learning By Sen Zhao, Yifan Guan, Jinyuan Ni, Gaojie Xu, Zhang Xu, Xiaoyu Lian, Yi Liu, Yi Wang, Wei Wang

Multi-granularity Adaptive Hypergraph Representation Learning via Granular-ball

Read the original on arXiv Machine Learning →

The paper introduces MGHRL, a framework for hypergraph representation learning that adapts hyperedge granularity through a granular-ball splitting strategy. It constructs hyperedges at multiple levels of detail, capturing high-order relationships tailored to the graph’s topology. A multi-granularity hypergraph network then processes these hyperedges with sub-networks and hierarchical reversible connections, achieving superior performance on benchmark datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 7

Global to Local: Topology-Preserving Adaptive Graph Pooling via Granular-Ball

The paper introduces Topology-Preserving Adaptive Graph Pooling (TPAGP), a method that partitions graphs into granular balls by combining node features and topology to create multi-granularity representations. TPAGP captures both global and local structural patterns, unlike prior pooling methods that coarsen graphs by removing or clustering nodes. Experiments show TPAGP outperforms existing pooling techniques on benchmark datasets, reducing information loss from fixed-granularity strategies.

By Sen Zhao, Gaojie Xu, Shuyin Xia, Yifan Guan, Yi Liu, Yi Wang, Wei Wang
ragbenchmarks
More like this →
arXiv AI
Aug 26

HMGCLIP: Heterogeneous Multi-Granularity Contrastive Learning for E-commerce Representation Learning

HMGCLIP is a unified multimodal embedding framework that uses a heterogeneous hypergraph to capture both fine‑grained and coarse‑grained product attributes. By mining structure‑aware hard negatives and aligning multi‑granular semantics at relation and hyperedge levels, it enables a dual‑granularity inference mechanism that dynamically fuses attribute evidence. Experiments on a new fine‑grained e‑commerce dataset and the public MAVE benchmark show that HMGCLIP outperforms strong multimodal encoders, MLLMs, and e‑commerce baselines.

By Qiuyu Zhu, Yi Gao, Zhichao Wan, Mingyang Ma
llmsragmultimodalbenchmarks
More like this →