Research map / Label-efficient and robust learning / Recognition and long-tail
Fidelity-Aware Recommendation Explanations via Stochastic Path Integration
Oren Barkan, Yahlly Schein, Yehonatan Elisha, Veronika Bogina, Mikhail Baklanov, Noam Koenigstein
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 stochastic baseline sampling to path integration (ablation) | PI · ML1M, VAE | POS@5: 0.236 -> 0.189 | Improved |
| add stochastic baseline sampling to path integration (ablation) | PI · ML1M, NCF | POS@5: 0.211 -> 0.185 | Improved |
| add stochastic baseline sampling to path integration (ablation) | PI · ML1M, MF | POS@5: 0.418 -> 0.410 | Improved |
| add stochastic baseline sampling to path integration (ablation) | PI · Yahoo! Music, VAE | CDCG: 0.380 -> 0.358 | Improved |
| add stochastic baseline sampling to path integration (ablation) | PI · ML1M, MF | INS: 0.939 -> 0.939 | No clear effect |
| add stochastic baseline sampling to path integration (ablation) | PI · Yahoo! Music, MF | DEL: 0.591 -> 0.591 | No clear effect |
| add stochastic baseline sampling to path integration (ablation) | PI · ML1M, VAE, Ke=2 | INS@Ke: 1.987 -> 3.626 | Improved |
| replace learned explainer LXR with SPINRec | LXR · ML1M, VAE | POS@5: 0.348 -> 0.189 | Improved |
| use SPINRec instead of FIA | FIA · Yahoo! Music, VAE | POS@5: 0.315 -> 0.280 | Improved |
| increase number of sampled baselines kappa beyond 10 (ablation) | SPINRec · ML1M, NCF | INS | No clear effect |
| use SPINRec instead of PI at fixed length Ke=2 (MF, ML1M) (ablation) | PI · ML1M, MF, Ke=2 | INS@Ke: 0.798 -> 0.799 | No clear effect |
| add stochastic sampling to PI at ML1M VAE (ablation) | PI · ML1M, VAE | INS: 0.029 -> 0.031 | Improved |
Closest papers by meaning
- NineRec: A Benchmark Dataset Suite for Evaluating Transferable Recommendation (TPAMI 2024 · similarity 0.88)
- Dynamic Explainable Recommendation Based on Neural Attentive Models (AAAI 2019 · similarity 0.88)
- CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence (NeurIPS 2024 · similarity 0.85)
- Coherency Improved Explainable Recommendation via Large Language Model (AAAI 2025 · similarity 0.85)
- Influential Exemplar Replay for Incremental Learning in Recommender Systems (AAAI 2024 · similarity 0.85)
- Knowledge-Aware Explainable Reciprocal Recommendation (AAAI 2024 · similarity 0.85)
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.
