Research map / Probabilistic and scientific modeling / Variational and generative sampling
Data Augmentation Based on Adversarial Autoencoder Handling Imbalance for Learning to Rank
Qian Yu, Wai Lam
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 AAE-generated data (Augment(R+Q)) | LambdaMART · MQ2007 | NDCG@5: 0.419 -> 0.439 | Improved |
| add AAE-generated data (Augment(R+Q)) | LambdaMART · MSLR-WEB10K | NDCG@5: 0.461 -> 0.496 | Improved |
| add AAE-generated data (Augment(R+Q)) | RankSVM · MQ2008 | NDCG@5: 0.450 -> 0.465 | Improved |
| add query-type augmentation on top of relevance augmentation (R+Q vs R) (ablation) | LambdaMART · MQ2007 | NDCG@5: 0.434 -> 0.439 | Improved |
| add query-type augmentation on top of relevance augmentation (R+Q vs R) (ablation) | LambdaMART · MSLR-WEB10K | NDCG@5: 0.489 -> 0.496 | Improved |
| undersample majority class | LambdaMART · MQ2007 | NDCG@5: 0.419 -> 0.391 | Hurt |
| random oversampling | LambdaMART · MQ2007 | NDCG@5: 0.419 -> 0.412 | No clear effect |
| SMOTE oversampling | LambdaMART · MQ2008 | NDCG@5: 0.469 -> 0.476 | No clear effect |
| set latent representation dimension too small or too large (ablation) | Augment(R+Q) · MQ2007/MQ2008 | P@1 | Hurt |
| increase number of query clusters (ablation) | Augment(R+Q) · MQ2007/MQ2008 | P@1 | Improved |
Closest papers by meaning
- Learning to Rank in Generative Retrieval (AAAI 2024 · similarity 0.84)
- A Statistical Framework for Data-dependent Retrieval-Augmented Models (ICML 2024 · similarity 0.83)
- Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off (AAAI 2024 · similarity 0.83)
- USTAD: Unified Single-model Training Achieving Diverse Scores for Information Retrieval (ICML 2024 · similarity 0.82)
- Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers (ICLR 2025 · similarity 0.82)
- On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains (ICML 2025 · similarity 0.81)
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.
