Research map / Probabilistic and scientific modeling / Dynamical systems
Leaping through Time with Gradient-Based Adaptation for Recommendation
Nuttapong Chairatanakul, Hoang NT, Xin Liu, Tsuyoshi Murata
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 |
|---|---|---|---|
| use LeapRec instead of the strongest reported baseline | recommendation model · Amazon | NDCG@5: 0.2140 -> 0.2391 | Improved |
| use LeapRec instead of the strongest reported baseline | recommendation model · Goodreads | NDCG@5: 0.3947 -> 0.4171 | Improved |
| use LeapRec instead of the strongest reported baseline | recommendation model · Yelp | NDCG@5: 0.5295 -> 0.5547 | Improved |
| add LeapRec to SASRec | SASRec · Amazon | NDCG@5: 0.1806 -> 0.2045 | Improved |
| add LeapRec to SASRec | SASRec · Goodreads | NDCG@5: 0.3701 -> 0.3956 | Improved |
| add LeapRec to LightGCN | LightGCN · Goodreads | NDCG@5 | Hurt |
| replace Leap trajectory-based learning with FOMAML (ablation) | GNN plug-in variants · reported GNN experiments | NDCG@5 | Hurt |
| use OTL only, with GTL unused (ablation) | LeapRec · Amazon | NDCG@5: 0.2384 -> 0.2416 | Improved |
| allocate dimensions as GTL 40 and OTL 121 (ablation) | LeapRec · Goodreads | NDCG@5: 0.4025 -> 0.4093 | Improved |
| allocate dimensions as GTL 121 and OTL 40 (ablation) | LeapRec · Yelp | NDCG@5: 0.5379 -> 0.5485 | Improved |
| add LeapRec to the neural recommender (ablation) | neural recommender · Amazon | HR@5: 0.0871 -> 0.1252 | Improved |
| add LeapRec to the neural recommender (ablation) | neural recommender · Goodreads | HR@5: 0.2256 -> 0.2452 | Improved |
Closest papers by meaning
- A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations (AAAI 2022 · similarity 0.88)
- Cold-start Sequential Recommendation via Meta Learner (AAAI 2021 · similarity 0.87)
- Future Sight and Tough Fights: Revolutionizing Sequential Recommendation with FENRec (AAAI 2025 · similarity 0.85)
- Temporal Graph Contrastive Learning for Sequential Recommendation (AAAI 2024 · similarity 0.84)
- Counterfactual Task-augmented Meta-learning for Cold-start Sequential Recommendation (AAAI 2025 · similarity 0.84)
- The Adaptive Q-Network for Recommendation Tasks with Dynamic Item Space (AAAI 2025 · similarity 0.83)
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.
