Research map / Architectures and efficiency / Attention and transformers
Dynamic Memory based Attention Network for Sequential Recommendation
Qiaoyu Tan, Jianwei Zhang, Ninghao Liu, Xiao Huang, Hongxia Yang, Jingren Zhou, Xia Hu
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 long-term attention to the short-term recurrent-attention model (ablation) | DMAN · Taobao | Recall@100: 0.237 -> 0.293 | Improved |
| add long-term attention to the short-term recurrent-attention model (ablation) | DMAN · XLong | Recall@100: 0.021 -> 0.054 | Improved |
| use dynamic memory abstraction instead of FIFO memory (ablation) | DMAN · Taobao | Recall@100: 0.263 -> 0.293 | Improved |
| use dynamic memory abstraction instead of FIFO memory (ablation) | DMAN · XLong | Recall@100: 0.036 -> 0.054 | Improved |
| extend attention context with the previous sequence's hidden state (ablation) | DMAN · Taobao | Recall@100: 0.257 -> 0.293 | Improved |
| extend attention context with the previous sequence's hidden state (ablation) | DMAN · XLong | Recall@100: 0.043 -> 0.054 | Improved |
| use DMAN rather than SDM | sequential recommendation · Taobao | HR@50: 21.66 -> 24.92 | Improved |
| use DMAN rather than SDM | sequential recommendation · JD.com | NDCG@100: 34.82 -> 36.93 | Improved |
| use DMAN rather than HPMN | long-sequence recommendation · XLong | Recall@200: 0.118 -> 0.132 | Improved |
| use DMAN rather than HPMN | long-sequence recommendation · XLong | Recall@500: 0.136 -> 0.163 | Improved |
Closest papers by meaning
- SLMRec: Distilling Large Language Models into Small for Sequential Recommendation (ICLR 2025 · similarity 0.90)
- Iterative Sparse Attention for Long-sequence Recommendation (AAAI 2025 · similarity 0.89)
- LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation (NeurIPS 2024 · similarity 0.88)
- MARS: Multi-resolution Adaptive Routing for Sequential Recommendation (NeurIPS 2026 · similarity 0.88)
- LLM4RSR: Large Language Models as Data Correctors for Robust Sequential Recommendation (AAAI 2025 · similarity 0.88)
- Customizing Language Models with Instance-wise LoRA for Sequential Recommendation (NeurIPS 2024 · 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.
