Research map / Label-efficient and robust learning / Recognition and long-tail
Multi-View Intent Disentangle Graph Networks for Bundle 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 multi-view intent disentangling with global and local graphs and intent contrast | MIDGN · NetEase | Recall@20: 0.0491 -> 0.0678 | Helped |
| Use multi-view intent disentangling with global and local graphs and intent contrast | MIDGN · Youshu | Recall@20: 0.2347 -> 0.2682 | Helped |
| Add local-view graph disentangling instead of replacing it with GCN (ablation) | MIDGN · NetEase | Recall@20: 0.0547 -> 0.0678 | Helped |
| Add local-view graph disentangling instead of replacing it with GCN (ablation) | MIDGN · Youshu | Recall@20: 0.2475 -> 0.2682 | Helped |
| Add global-view graph disentangling instead of replacing it with GCN (ablation) | MIDGN · NetEase | Recall@20: 0.0583 -> 0.0678 | Helped |
| Add global-view graph disentangling instead of replacing it with GCN (ablation) | MIDGN · Youshu | Recall@20: 0.2464 -> 0.2682 | Helped |
| Add intent contrast between global and local views (ablation) | MIDGN · NetEase | Recall@20: 0.0609 -> 0.0678 | Helped |
| Add intent contrast between global and local views (ablation) | MIDGN · Youshu | Recall@20: 0.2588 -> 0.2682 | Helped |
| Increase disentangling layers from 1 to 3 (ablation) | MIDGN · NetEase | Recall@20: 0.0442 -> 0.0642 | Helped |
| Increase disentangling layers from 3 to 4 (ablation) | MIDGN · Youshu | Recall@20: 0.2682 -> 0.2617 | Hurt |
| Use a single intent rather than four (ablation) | MIDGN · NetEase | Recall@20: 0.0678 -> 0.0579 | Hurt |
| Increase intent count from 4 to 8 (ablation) | MIDGN · NetEase | Recall@20: 0.0678 -> 0.0587 | Hurt |
Closest papers by meaning
- Disentangled Contrastive Bundle Recommendation with Conditional Diffusion (AAAI 2025 · similarity 0.89)
- DisCo: Graph-Based Disentangled Contrastive Learning for Cold-Start Cross-Domain Recommendation (AAAI 2025 · similarity 0.84)
- End-to-end Learnable Clustering for Intent Learning in Recommendation (NeurIPS 2024 · similarity 0.83)
- Tree of Preferences for Diversified Recommendation (NeurIPS 2025 · similarity 0.83)
- Disentangled Modeling of Preferences and Social Influence for Group Recommendation (AAAI 2025 · similarity 0.83)
- ScoreNet: Consistency-driven Framework with Multi-side Information Fusion for Session-based Recommendation (AAAI 2025 · similarity 0.82)
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.