Research map / Learning theory and algorithms / Prediction and decision losses
Uniform Sequence Better: Time Interval Aware Data Augmentation for Sequential 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 time-interval-aware augmentation instead of CoSeRec's traditional augmentation | CoSeRec · Beauty | NDCG@10: 0.0381 -> 0.0421 | Helped |
| Use time-interval-aware augmentation instead of CoSeRec's traditional augmentation | CoSeRec · Sports | NDCG@10: 0.0241 -> 0.0282 | Helped |
| Use time-interval-aware augmentation instead of CoSeRec's traditional augmentation | CoSeRec · Home | NDCG@10: 0.0136 -> 0.0153 | Helped |
| Use time-interval-aware augmentation instead of CoSeRec's traditional augmentation | CoSeRec · Yelp | NDCG@10: 0.0322 -> 0.0371 | Helped |
| Train on uniform rather than non-uniform sequences | CoSeRec · Beauty, Sports, Home, Yelp | NDCG@10 | Helped |
| Replace one time-interval-aware operator with its traditional counterpart (ablation) | TiCoSeRec · Sports and Home | Recommendation accuracy | Hurt |
| Replace Ti-Substitute with traditional Substitute (ablation) | TiCoSeRec · Sports and Home | Recommendation accuracy | Hurt |
| Replace Ti-Reorder with traditional Reorder (ablation) | TiCoSeRec · Sports and Home | Hit ratio | Hurt |
| Use Ti-Insert, Ti-Crop, Ti-Mask, Ti-Reorder, and Ti-Substitute together (ablation) | TiCoSeRec · Sports and Home | Recommendation accuracy | Helped |
| Set the uniform-sequence threshold ratio σ to 0.2 or 0.3 rather than σ=0 (ablation) | TiCoSeRec · Four datasets | Recommendation accuracy | Helped |
| Increase σ beyond 0.4 (ablation) | TiCoSeRec · Four datasets | Recommendation accuracy | Hurt |
| Apply Crop, Reorder, Mask, Insert, and Substitute without time-interval guidance (ablation) | TiCoSeRec · Sports and Home | Recommendation accuracy | Hurt |
Closest papers by meaning
- Augmenting Sequential Recommendation with Balanced Relevance and Diversity (AAAI 2025 · similarity 0.91)
- LLM4RSR: Large Language Models as Data Correctors for Robust Sequential Recommendation (AAAI 2025 · similarity 0.87)
- Temporal Graph Contrastive Learning for Sequential Recommendation (AAAI 2024 · similarity 0.86)
- Future Sight and Tough Fights: Revolutionizing Sequential Recommendation with FENRec (AAAI 2025 · similarity 0.86)
- LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation (NeurIPS 2024 · similarity 0.86)
- UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence (NeurIPS 2026 · similarity 0.86)
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.