CoLES: Contrastive Learning for Event Sequences with Self-Supervision
Summary: CoLES adapts contrastive self-supervision to discrete event sequences, producing fixed-length embeddings for downstream tasks. Real-world deployment at a large European financial services company yields hundreds of millions in annual gains, with public datasets showing consistent improvements over baselines. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Dmitrii Babaev (Artificial Intelligence Research Institute; Sber AI Lab)
- 2. Nikita Ovsov (Sber AI Lab)
- 3. Ivan Kireev (Sber AI Lab)
- 4. Maria Ivanova (Sber AI Lab)
- 5. Gleb Gusev (Moscow Institute of Physics and Technology; Sber AI Lab)
- 6. Ivan Nazarov (Artificial Intelligence Research Institute)
- 7. Alexander Tuzhilin (New York University)
BibTeX Citation
@inproceedings{babaev_sigmod22,
title = {{CoLES: Contrastive Learning for Event Sequences with Self-Supervision}},
author = {Babaev, Dmitrii and Ovsov, Nikita and Kireev, Ivan and Ivanova, Maria and Gusev, Gleb and Nazarov, Ivan and Tuzhilin, Alexander},
series = {{SIGMOD} '22},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3514221.3526129},
url = {https://dl.acm.org/doi/10.1145/3514221.3526129},
year = {2022}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,330 | SWIFT: Enabling Large-Scale Temporal Graph Learning on a Single Machine | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 0 of 0 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next