What question did this study set out to answer?

This research aims to improve service recommendation systems by addressing the challenges of heterophily and user-item interactions.

H2OGNN: Hypergraph-based heterophily-aware neural network for service recommendation

View Full Paper

Ask AI

Bookmark

Authors

A new model enhances service recommendation accuracy by leveraging unique interaction patterns in users and services.

This research aims to improve service recommendation systems by addressing the challenges of heterophily and user-item interactions.
Developed H2OGNN model utilizing hypergraph structures
Integrated a heterophily-aware attention mechanism
Implemented a dynamic multi-interest learning module
Conducted experiments on Steam, MovieLens, and Yelp datasets
H2OGNN outperformed the state-of-the-art HMGSR by approximately 14.1% on Steam
Achieved a 12.0% improvement on MovieLens and a 13.9% gain on Yelp
Demonstrated robustness across multiple datasets and consistent superior performance.

Qian et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

A new model enhances service recommendation accuracy by leveraging unique interaction patterns in users and services.

This research aims to improve service recommendation systems by addressing the challenges of heterophily and user-item interactions.
Developed H2OGNN model utilizing hypergraph structures
Integrated a heterophily-aware attention mechanism
Implemented a dynamic multi-interest learning module
Conducted experiments on Steam, MovieLens, and Yelp datasets
H2OGNN outperformed the state-of-the-art HMGSR by approximately 14.1% on Steam
Achieved a 12.0% improvement on MovieLens and a 13.9% gain on Yelp
Demonstrated robustness across multiple datasets and consistent superior performance.

Qian et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark