Schuyler: Self-Supervised Clustering of Tables in Relational Databases
Summary: Schuyler clusters relational tables by combining schema/structural and semantic signals, fine-tuning a large language model with self-supervised triplet loss to produce embeddings with no labeled data. On a new five-DB benchmark (29–481 tables, 3–47 clusters) it improves prior art by +0.13 ARI and +0.10 AMI. (summarized by gpt-5-mini on Mar 13 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Lukas Laskowski
- 2. Fabian Panse
- 3. Michael Hladik
- 4. Jan Portisch
- 5. Felix Naumann
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 4 of 4 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 270 | OPTICS: Ordering Points To Identify the Clustering Structure | 1999 | SIGMOD | 0.00029505642 |
| 1,510 | Summarizing Relational Databases | 2009 | VLDB | 0.00011606901 |
| 3,426 | Discovering Topical Structures of Databases | 2008 | SIGMOD | 7.1063105e-05 |
| 3,536 | General purpose database summarization | 2005 | VLDB | 6.9990821e-05 |
Previous
Page 1 / 1
Next