Deep Indexed Active Learning for Matching Heterogeneous Entity Representations
Summary: Presents DIAL, an ER method with active learning that jointly learns embeddings to boost blocking recall and matching accuracy. Index-By-Committee with PLM-based blockers and matchers; blocking vs. matching have distinct training aims, improving precision, recall, and speed on five benchmarks. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Arjit Jain
- 2. Sunita Sarawagi
- 3. Prithviraj Sen
Incoming Citations (Sorted by Pagerank)
Showing 5 of 5 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 8,908 | Deep Active Alignment of Knowledge Graph Entities and Schemata | 2023 | SIGMOD | 4.427232e-05 |
| 9,460 | The Battleship Approach to the Low Resource Entity Matching Problem | 2023 | SIGMOD | 4.3366491e-05 |
| 9,855 | Progressive Entity Matching: A Design Space Exploration | 2025 | SIGMOD | 4.269353e-05 |
| 9,873 | CORAL: Collaborative Automatic Labeling System based on Large Language Models | 2024 | VLDB | 4.2667743e-05 |
| 10,040 | 3dSAGER: Geospatial Entity Resolution over 3D Objects | 2026 | SIGMOD | 4.1945683e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 17 of 17 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next