mlsanityData to 7 Oct 2026

CoLES: Contrastive Learning for Event Sequences with Self-Supervision

arXiv 2002.08232 ↗First posted 19 Feb 2020cs.LGcited by 32

Not on the map. Why?

Abstract (arXiv)

We address the problem of self-supervised learning on discrete event sequences generated by real-world users. Self-supervised learning incorporates complex information from the raw data in low-dimensional fixed-length vector representations that could be easily applied in various downstream machine learning tasks. In this paper, we propose a new method "CoLES", which adapts contrastive learning, previously used for audio and computer vision domains, to the discrete event sequences domain in a self-supervised setting. We deployed CoLES embeddings based on sequences of transactions at the large European financial services company. Usage of CoLES embeddings significantly improves the performance of the pre-existing models on downstream tasks and produces significant financial gains, measured in hundreds of millions of dollars yearly. We also evaluated CoLES on several public event sequences datasets and showed that CoLES representations consistently outperform other methods on different downstream tasks.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 10; 2025: 7; 2026: 9.

32 papers.

Sort:

By area:

  1. 2023LightPath: Lightweight and Scalable Path Representation Learningcited by 32
  2. 2024Towards a Foundation Purchasing Model: Pretrained Generative Autoregression on Transaction Sequencescited by 11
  3. 2024HoTPP Benchmark: Are We Good at the Long Horizon Events Forecasting?cited by 11
  4. 2024Multimodal Banking Dataset: Understanding Client Needs through Event Sequencescited by 9
  5. 2024MLEM: Generative and Contrastive Learning as Distinct Modalities for Event Sequencescited by 6
  6. 2024EBES: Easy Benchmarking for Event Sequencescited by 6
  7. 2024Learning Transactions Representations for Information Management in Banks: Mastering Local, Global, and External Knowledgecited by 5
  8. 2023Label Attention Network for Temporal Sets Prediction: You Were Looking at a Wrong Self-Attentioncited by 2
  9. 2024Uniting contrastive and generative learning for event sequences modelscited by 2
  10. 2025LATTE: Learning Aligned Transactions and Textual Embeddings for Bank Clientscited by 2
  11. 2025Open Banking Foundational Model: Learning Language Representations from Few Financial Transactionscited by 2
  12. 2025Topological Metric for Unsupervised Embedding Quality Evaluationcited by 2
20 more
  1. 2022The Long Tail of Context: Does it Exist and Matter?cited by 1
  2. 2023Hiding Backdoors within Event Sequence Data via Poisoning Attackscited by 1
  3. 2024Locally Differentially Private Embedding Models in Distributed Fraud Prevention Systemscited by 1
  4. 2024ESQA: Event Sequences Question Answeringcited by 1
  5. 2026Embedding-Aware Feature Discovery: Bridging Latent Representations and Interpretable Features in Event Sequencescited by 1
  6. 2023Continuous-time convolutions model of event sequencescited by 0
  7. 2023Designing an attack-defense game: how to increase robustness of financial transaction models via a competitioncited by 0
  8. 2024Self-Attention Mechanism in Multimodal Context for Banking Transaction Flowcited by 0
  9. 2025Towards Unified Approaches in Self-Supervised Event Stream Modeling: Progress and Prospectscited by 0
  10. 2025Looking around you: external information enhances representations for event sequencescited by 0
  11. 2025How to model Human Actions distribution with Event Sequence Datacited by 0
  12. 2025Automated Evolutionary Optimization for Resource-Efficient Neural Network Trainingcited by 0
  13. 2026Beyond Isolated Clients: Integrating Graph-Based Embeddings into Event Sequence Modelscited by 0
  14. 2026When Losses Align: Gradient-Based Composite Loss Weighting for Efficient Pretrainingcited by 0
  15. 2026SOHET: Sequence Of Heterogeneous Events Transformer with Self-Supervised Pre-Trainingcited by 0
  16. 2026A Foundation Model for Multimodal Event Sequences in Financial Applicationscited by 0
  17. 2026User-Centric Modeling of Transactional Sequences with Explainable State Space Modelscited by 0
  18. 2026MINT: A Universal Zero-Shot Predictor for Transaction Datacited by 0
  19. 2026FINESSE: An Agent-Based Simulator and Benchmark Dataset for Multimodal Financial Event Sequencescited by 0
  20. 2026From "Who Is This User?" to "What Does This Purchase Mean?": A Deployed Pipeline for Semantic User Profiling at Bank Scalecited by 0