Research map / Graph learning / Knowledge and temporal graphs
Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior Recommendation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use KHGT instead of KGAT | Multi-behavior recommendation · Yelp | HR@10: 0.835 -> 0.880 | Helped |
| Use KHGT instead of KGAT | Multi-behavior recommendation · Yelp | NDCG@10: 0.543 -> 0.603 | Helped |
| Use KHGT instead of MATN | Multi-behavior recommendation · MovieLens | HR@10: 0.847 -> 0.861 | Helped |
| Use KHGT instead of MATN | Multi-behavior recommendation · MovieLens | NDCG@10: 0.569 -> 0.597 | Helped |
| Use KHGT instead of KGAT | Multi-behavior recommendation · Online Retail | HR@10: 0.377 -> 0.464 | Helped |
| Use KHGT instead of MBGCN | Multi-behavior recommendation · Online Retail | NDCG@10: 0.222 -> 0.278 | Helped |
| Replace attentive heterogeneous aggregation with graph convolution (ablation) | KHGT · Reported ablation evaluation | Recommendation performance | Hurt |
| Remove the mutual relation encoder (ablation) | KHGT · Reported ablation evaluation | Recommendation performance | Hurt |
| Replace gated fusion with mean pooling (ablation) | KHGT · Reported ablation evaluation | Recommendation performance | Hurt |
| Remove temporal context embeddings (ablation) | KHGT · Reported ablation evaluation | Recommendation performance | Hurt |
| Remove item-item relations (ablation) | KHGT · Reported ablation evaluation | Recommendation performance | Hurt |
| Include all available behavior types rather than only the target or a subset (ablation) | KHGT · Yelp and Online Retail | Recommendation performance | Helped |
Closest papers by meaning
- DOGE: LLMs-Enhanced Hyper-Knowledge Graph Recommender for Multimodal Recommendation (AAAI 2025 · similarity 0.89)
- Bridging the User-side Knowledge Gap in Knowledge-aware Recommendations with Large Language Models (AAAI 2025 · similarity 0.88)
- LGMRec: Local and Global Graph Learning for Multimodal Recommendation (AAAI 2024 · similarity 0.87)
- Language Representations Can be What Recommenders Need: Findings and Potentials (ICLR 2025 · similarity 0.87)
- Mind Individual Information! Principal Graph Learning for Multimedia Recommendation (AAAI 2025 · similarity 0.87)
- Semantic Enhanced Heterogeneous Hypergraph Network for Collaborative Filtering (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.