Research map / Learning theory and algorithms / Fairness
Revisiting Fairness-aware Interactive Recommendation: Item Lifecycle as a Control Knob
Yun Lu, Xiaoyu Shi, Hong Xie, Chongjun Xia, Zhenhui Gong, Mingsheng Shang
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 lifecycle-aware rewards to the hierarchical agent (ablation) | LHRL · KuaiRec | Cumulative Reward (Rcum): 13.226 -> 15.613 | Improved |
| add lifecycle-aware rewards to the hierarchical agent (ablation) | LHRL · KuaiRand | Cumulative Reward (Rcum): 9.712 -> 12.655 | Improved |
| add lifecycle-aware rewards to the hierarchical agent (ablation) | LHRL · KuaiRec | Absolute Difference (AD): 0.037 -> 0.009 | Improved |
| add hierarchical (two-level) structure (ablation) | LHRL · KuaiRec | Interaction Length (Len): 10.700 -> 17.760 | Improved |
| add hierarchical (two-level) structure (ablation) | LHRL · KuaiRand | Cumulative Reward (Rcum): 8.262 -> 12.655 | Improved |
| combine lifecycle rewards and hierarchy versus flat agent (ablation) | LHRL · KuaiRec | Cumulative Reward (Rcum): 8.460 -> 15.613 | Improved |
| add lifecycle module to SAC4IR | SAC4IR · KuaiRec | Cumulative Reward (Rcum): 11.412 -> 12.346 | Improved |
| add lifecycle module to FCPO | FCPO · KuaiRand | Cumulative Reward (Rcum): 11.023 -> 11.650 | Improved |
| add lifecycle module to DNAIR | DNAIR · KuaiRec | Cumulative Reward (Rcum): 7.445 -> 8.078 | Improved |
| add lifecycle module to SAC4IR | SAC4IR · KuaiRand | Cumulative Reward (Rcum): 6.779 -> 6.768 | No clear effect |
| add lifecycle module to DNAIR | DNAIR · KuaiRand | Cumulative Reward (Rcum): 6.895 -> 6.894 | No clear effect |
| add lifecycle module to SAC4IR | SAC4IR · KuaiRec | Absolute Difference (AD): 0.012 -> 0.013 | No clear effect |
Closest papers by meaning
- Interpolating Item and User Fairness in Multi-Sided Recommendations (NeurIPS 2024 · similarity 0.84)
- Listwise Preference Diffusion Optimization for User Behavior Trajectories Prediction (NeurIPS 2025 · similarity 0.84)
- Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders (NeurIPS 2026 · similarity 0.84)
- On the Unexpected Effectiveness of Reinforcement Learning for Sequential Recommendation (ICML 2024 · similarity 0.83)
- On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders (NeurIPS 2025 · similarity 0.83)
- Contrastive Representation for Interactive Recommendation (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.
