Research map / Label-efficient and robust learning / Recognition and long-tail
Prompt-Based Multi-Interest Learning Method for Sequential Recommendation
Xue Dong, Xuemeng Song, Tongliang Liu, Weili Guan
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 learnable prompt embeddings to the extractor and aggregator inputs (ablation) | PoMRec base · ML-1M | Recall@5: 0.3068 -> 0.3129 | Improved |
| add learnable prompt embeddings (ablation) | PoMRec base · Beauty | Recall@5: 0.1193 -> 0.1299 | Improved |
| add learnable prompt embeddings (ablation) | PoMRec base · Movies & TV | Recall@5: 0.2429 -> 0.2498 | Improved |
| add dispersion (variance) embedding to centrality (ablation) | PoMRec base · ML-1M | Recall@5: 0.3068 -> 0.3108 | Improved |
| add dispersion (variance) embedding to centrality (ablation) | PoMRec base · Beauty | Recall@5: 0.1193 -> 0.1293 | Improved |
| add dispersion (variance) embedding to centrality (ablation) | PoMRec base · Movies & TV | Recall@5: 0.2429 -> 0.2591 | Improved |
| add both prompts and dispersion (ablation) | PoMRec base · Beauty | Recall@5: 0.1193 -> 0.1456 | Improved |
| add both prompts and dispersion (ablation) | PoMRec base · Movies & TV | Recall@5: 0.2429 -> 0.2747 | Improved |
| deploy prompts and dispersion on MINER | MINER · ML-1M | Recall@5: 0.2758 -> 0.2975 | Improved |
| deploy prompts and dispersion on TiMiRec (single item embedding) | TiMiRec · ML-1M | Recall@5: 0.3091 -> 0.3222 | Improved |
| deploy prompts and dispersion on TiMiRec | TiMiRec · Movies & TV | Recall@5: 0.2506 -> 0.2735 | Improved |
| vary number of user interests K from 1 to 5 (ablation) | PoMRec · ML-1M / Movies & TV | Recall@5: best K=2 on ML-1M, K=3 on Movies & TV | Mixed |
Closest papers by meaning
- Auto Encoding Neural Process for Multi-interest Recommendation (AAAI 2025 · similarity 0.87)
- LGMRec: Local and Global Graph Learning for Multimodal Recommendation (AAAI 2024 · similarity 0.86)
- SLMRec: Distilling Large Language Models into Small for Sequential Recommendation (ICLR 2025 · similarity 0.86)
- Plug-In Diffusion Model for Sequential Recommendation (AAAI 2024 · similarity 0.86)
- Customizing Language Models with Instance-wise LoRA for Sequential Recommendation (NeurIPS 2024 · similarity 0.85)
- Augmenting Sequential Recommendation with Balanced Relevance and Diversity (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.
