Research map / Label-efficient and robust learning / Recognition and long-tail
Exploiting Inter-Session Information with Frequency-enhanced Dual-Path Networks for Sequential Recommendation
Peng He, Yanglei Gan, Tingting Dai, Run Lin, Xuexin Li, Yao Liu, Qiao Liu
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 Global Spectral Aggregator (inter-session path) (ablation) | FreqRec · Beauty | HR@20: 0.1202 -> 0.1359 | Improved |
| add Local Spectral Refiner (intra-session path) (ablation) | FreqRec · Beauty | HR@20: 0.1215 -> 0.1359 | Improved |
| add both GSA and LSR frequency modules on top of self-attention (ablation) | FreqRec · Toys & Games | HR@20: 0.0956 -> 0.1468 | Improved |
| add frequency-domain consistency loss LF (ablation) | FreqRec · Toys & Games | HR@20: 0.1342 -> 0.1468 | Improved |
| keep cross-entropy loss alongside frequency loss (ablation) | FreqRec · Beauty | HR@20: 0.1081 -> 0.1359 | Improved |
| add the self-attention branch to FreqNet (ablation) | FreqRec · Beauty | HR@20: 0.1279 -> 0.1359 | Improved |
| use parallel instead of serial fusion of inter and intra paths (ablation) | FreqRec · Beauty | HR@10: 0.0962 -> 0.0989 | Improved |
| use parallel instead of serial fusion (ablation) | FreqRec · Toys & Games | NDCG@10: 0.0655 -> 0.0653 | No clear effect |
| add the frequency-domain loss LF to SASRec | SASRec · Beauty | HR@10: 0.0531 -> 0.0592 | Improved |
| add the frequency-domain loss LF to BSARec | BSARec · Beauty | HR@10: 0.0871 -> 0.0972 | Improved |
| add the frequency-domain loss LF to DuoRec | DuoRec · Toys & Games | HR@10: 0.1027 -> 0.1030 | No clear effect |
| remove GSA from FreqRec under noisy cross-domain training (ablation) | FreqRec · Automotive (noisy) | HR@10: 0.0495 -> 0.0521 | Improved |
Closest papers by meaning
- Future Sight and Tough Fights: Revolutionizing Sequential Recommendation with FENRec (AAAI 2025 · similarity 0.87)
- SLMRec: Distilling Large Language Models into Small for Sequential Recommendation (ICLR 2025 · similarity 0.85)
- Enhancing Long-and Short-Term Representations for Next POI Recommendations via Frequency and Hierarchical Contrastive Learning (AAAI 2025 · similarity 0.85)
- LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation (NeurIPS 2024 · similarity 0.84)
- MARS: Multi-resolution Adaptive Routing for Sequential Recommendation (NeurIPS 2026 · similarity 0.84)
- Structured Spectral Reasoning for Frequency-Adaptive Multimodal Recommendation (NeurIPS 2025 · similarity 0.84)
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.
