Research map / Probabilistic and scientific modeling / Causal discovery
Adversarial Counterfactual Learning and Evaluation for Recommender System
Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, Kannan Achan
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 |
|---|---|---|---|
| Use adversarial counterfactual learning with Attn for both recommendation models | Attn · MovieLens-1M | Hit@10: 82.66 -> 83.64 | Improved |
| Use adversarial counterfactual learning with Attn for both recommendation models | Attn · MovieLens-1M | NDCG@10: 55.27 -> 55.71 | Improved |
| Use adversarial counterfactual learning with GMF for both recommendation models | GMF · LastFM | Hit@10: 83.12 -> 83.64 | Improved |
| Use adversarial counterfactual learning with Attn for both recommendation models | Attn · LastFM | NDCG@10: 59.75 -> 59.45 | Hurt |
| Use adversarial counterfactual learning with Attn for both recommendation models | Attn · Goodreads | Hit@10: 72.63 -> 73.82 | Improved |
| Use adversarial counterfactual learning with Attn for both recommendation models | Attn · Goodreads | NDCG@10: 48.98 -> 49.99 | Improved |
| Evaluate with learned worst-case propensity weighting rather than standard offline evaluation | Offline evaluation · Walmart.com online experiments | MSE on Hit@5: .18(.10) -> .12(.04) | Improved |
| Evaluate with learned worst-case propensity weighting rather than standard offline evaluation | Offline evaluation · Walmart.com online experiments | MSE on NDCG@5: .10(.06) -> .07(.03) | Improved |
Closest papers by meaning
- Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation (NeurIPS 2024 · similarity 0.87)
- Alleviating Dual Biases in Recommendation (Student Abstract) (AAAI 2025 · similarity 0.87)
- CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence (NeurIPS 2024 · similarity 0.84)
- Social Recommendation via Graph-Level Counterfactual Augmentation (AAAI 2025 · similarity 0.84)
- Sim4Rec: Data-Free Model Extraction Attack on Sequential Recommendation (AAAI 2025 · similarity 0.84)
- Addressing Hidden Confounding with Heterogeneous Observational Datasets for Recommendation (NeurIPS 2024 · 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.
