Falcon: Fair Active Learning using Multi-armed Bandits
Summary: Falcon: scalable fair active learning that boosts group fairness during dataset curation by using a postpone-on-mismatch trial-and-error sampler to target desired (protected,label) groups despite unknown labels. It encodes the informativeness vs postpone-rate trade-off as policies and uses adversarial multi-armed bandits to pick the best policy, yielding substantially better fairness–accuracy tradeoffs and efficiency. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Ki Hyun Tae
- 2. Hantian Zhang
- 3. Jaeyoung Park
- 4. Kexin Rong
- 5. Steven Euijong Whang
Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 9,587 | Low Rank Learning for Offline Query Optimization | 2025 | SIGMOD | 4.3215645e-05 |
| 9,644 | Fair and Actionable Causal Prescription Ruleset | 2025 | SIGMOD | 4.3109001e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 11 of 11 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next