Research map / Graph learning / Knowledge and temporal graphs
Multi-Granular Graph Learning with Fine-Grained Behavioral Pattern Awareness for Session-Based Recommendation
Ming Li, Zihao Yan, Yuting Chen, Lixin Cui, Lu Bai, Feilong Cao, Ke Lv, Zhao Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add item view (short-term intent from recent items) (ablation) | GraphFine · Tmall | HR@20: 34.42 -> 48.48 | Improved |
| add item view (ablation) | GraphFine · Yoochoose | HR@20: 72.23 -> 72.64 | No clear effect |
| add contextual aggregation network (ablation) | GraphFine · Tmall | HR@20: 47.59 -> 48.48 | Improved |
| add contextual aggregation network (ablation) | GraphFine · Yoochoose | MRR@20: 31.94 -> 31.95 | No clear effect |
| add item semantic network (ablation) | GraphFine · RetailRocket | HR@20: 58.52 -> 58.85 | Improved |
| add segmented hypergraph network (ablation) | GraphFine · Tmall | HR@20: 48.34 -> 48.48 | No clear effect |
| add segment view (ablation) | GraphFine · RetailRocket | HR@20: 58.43 -> 58.85 | Improved |
| add session view (ablation) | GraphFine · Yoochoose | HR@20: 72.63 -> 72.64 | No clear effect |
| add multi-view intent readout (item + segment views) | SR-GNN · Tmall | HR@20: 28.80 -> 36.19 | Improved |
| add multi-view intent readout (item + segment views) | GCE-GNN · Tmall | HR@20: 32.75 -> 36.07 | Improved |
| add multi-view intent readout (item + segment views) | GCE-GNN · Yoochoose | HR@20: 72.01 -> 72.01 | No clear effect |
| add segment view only | SR-GNN · Tmall | HR@20: 28.80 -> 29.39 | No clear effect |
Closest papers by meaning
- LS-TGNN: Long and Short-Term Temporal Graph Neural Network for Session-Based Recommendation (AAAI 2025 · similarity 0.88)
- Dynamic Multi-Interest Graph Neural Network for Session-Based Recommendation (AAAI 2025 · similarity 0.87)
- Temporal Graph Contrastive Learning for Sequential Recommendation (AAAI 2024 · similarity 0.86)
- Mind Individual Information! Principal Graph Learning for Multimedia Recommendation (AAAI 2025 · similarity 0.86)
- Ready for You When You Are Back: Content-Driven Session-Based Recommendation for Continuity of Experience (AAAI 2025 · similarity 0.85)
- ScoreNet: Consistency-driven Framework with Multi-side Information Fusion for Session-based Recommendation (AAAI 2025 · similarity 0.85)
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.
