Research map / Learning theory and algorithms / Prediction and decision losses
Active Ordinal Querying for Tuplewise Similarity Learning
Gregory Canal, Stefano Fenu, Christopher Rozell
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 InfoTuple adaptive selection instead of CKL triplet selection | Similarity embedding learning · Synthetic datasets | Kendall's Tau | Improved |
| Use InfoTuple adaptive selection instead of random query selection | Similarity embedding learning · Synthetic datasets | Kendall's Tau | Improved |
| Increase InfoTuple tuple size from triplets to larger tuples | InfoTuple · Synthetic datasets | Kendall's Tau | Improved |
| Increase tuple size from triplets to larger tuples | InfoTuple · Food-10k human responses | holdout accuracy | Improved |
| Use InfoTuple adaptive selection instead of random query selection | Similarity embedding learning · Food-10k human responses | holdout accuracy | Improved |
| Increase tuple size from triplets to 5-tuples | Human oracle responses · Food-10k human responses | coherence: p=0.007181 | Improved |
| Increase tuple size to moderate sizes | Human labelers · Random tuple timing study | response time | Mixed |
| Use larger tuples instead of triplets | Similarity embedding learning · Synthetic datasets | Kendall's Tau | Improved |
| Use random queries of different tuple sizes | Random query selection · Synthetic datasets | Kendall's Tau | No clear effect |
Closest papers by meaning
- Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls (ICML 2026 · similarity 0.84)
- Ranking with Multiple Oracles: From Weak to Strong Stochastic Transitivity (ICML 2025 · similarity 0.83)
- Active Seriation: Efficient Ordering Recovery with Statistical Guarantees (NeurIPS 2025 · similarity 0.83)
- Learning-Augmented Search Data Structures (ICLR 2025 · similarity 0.82)
- Data Pruning by Information Maximization (ICLR 2025 · similarity 0.82)
- LotusFilter: Fast Diverse Nearest Neighbor Search via a Learned Cutoff Table (CVPR 2025 · similarity 0.82)
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.
