Research map / Image generation / Fast diffusion sampling
Adaptive Diffusion-based Augmentation for Recommendation
Na Li, Fanghui Sun, Yan Zou, Yangfu Zhu, Xiatian Zhu, Ying Ma
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 ADAR diffusion-based negative augmentation | NGCF · Amazon-Beauty | Recall@10: 6.37 -> 8.13 | Improved |
| add ADAR | LightGCN · Amazon-Beauty | Recall@10: 8.69 -> 8.99 | Improved |
| add ADAR | MixGCF · Amazon-Beauty | Recall@10: 9.82 -> 10.01 | Improved |
| add ADAR | AHNS · Amazon-Beauty | Recall@10: 9.66 -> 10.05 | Improved |
| add ADAR | GRU4Rec · Amazon-Beauty | Recall@10: 2.79 -> 4.34 | Improved |
| add ADAR | SASRec · Yelp | Recall@10: 2.99 -> 3.30 | Improved |
| add ADAR | CL4SRec · Yelp | NDCG@10: 1.60 -> 1.82 | Improved |
| use adaptive t* instead of randomly sampled t* (ablation) | ADAR on NGCF · Amazon-Beauty | Recall@10: 7.81 -> 8.13 | Improved |
| use adaptive t* instead of fixed t* at T/2 (ablation) | ADAR on NGCF · Amazon-Beauty | Recall@10: 7.79 -> 8.13 | Improved |
| use adaptive t* instead of mixing several fixed t (ablation) | ADAR on NGCF · Amazon-Beauty | Recall@10: 7.91 -> 8.13 | Improved |
| use adaptive t* instead of randomly sampled t* (ablation) | ADAR on GRU4Rec · Amazon-Beauty | Recall@10: 4.00 -> 4.34 | Improved |
| use adaptive t* instead of fixed t* at T/2 (ablation) | ADAR on GRU4Rec · Amazon-Beauty | Recall@10: 3.37 -> 4.34 | Improved |
Closest papers by meaning
- On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders (NeurIPS 2025 · similarity 0.89)
- Plug-In Diffusion Model for Sequential Recommendation (AAAI 2024 · similarity 0.88)
- Adaptive Hardness Negative Sampling for Collaborative Filtering (AAAI 2024 · similarity 0.88)
- Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation (NeurIPS 2025 · similarity 0.88)
- Preference Diffusion for Recommendation (ICLR 2025 · similarity 0.88)
- Enhancing Diffusion Model with Auxiliary Information Mining-Exploration and Efficient Sampling Mechanism for Sequential Recommendation (AAAI 2025 · similarity 0.88)
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.
