mlsanityData to 7 Oct 2026

SeqNAS: Neural Architecture Search for Event Sequence Classification

arXiv 2401.03246 ↗First posted 6 Jan 2024cs.LG cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Neural Architecture Search (NAS) methods are widely used in various industries to obtain high quality taskspecific solutions with minimal human intervention. Event Sequences find widespread use in various industrial applications including churn prediction customer segmentation fraud detection and fault diagnosis among others. Such data consist of categorical and real-valued components with irregular timestamps. Despite the usefulness of NAS methods previous approaches only have been applied to other domains images texts or time series. Our work addresses this limitation by introducing a novel NAS algorithm SeqNAS specifically designed for event sequence classification. We develop a simple yet expressive search space that leverages commonly used building blocks for event sequence classification including multihead self attention convolutions and recurrent cells. To perform the search we adopt sequential Bayesian Optimization and utilize previously trained models as an ensemble of teachers to augment knowledge distillation. As a result of our work we demonstrate that our method surpasses state of the art NAS methods and popular architectures suitable for sequence classification and holds great potential for various industrial applications.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 37 of its 57 references that are in the map. First posted on arXiv 6 Jan 2024.

Builds on

37 of 57 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  4. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  5. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  6. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  7. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
  8. 2018The UCR Time Series Archivecited by 421
  9. 2020NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Searchcited by 412
  10. 2018How Does Batch Normalization Help Optimization?cited by 355
  11. 2019NAS-Bench-101: Towards Reproducible Neural Architecture Searchcited by 340
  12. 2019ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernelscited by 336
25 more
  1. 2019Random Search and Reproducibility for Neural Architecture Searchcited by 253
  2. 2020Transformer Hawkes Processcited by 230
  3. 2014Efficient Object Localization Using Convolutional Networkscited by 226
  4. 2018CatBoost: gradient boosting with categorical features supportcited by 208
  5. 2019BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Searchcited by 175
  6. 2021Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillationcited by 131
  7. 2021CKConv: Continuous Kernel Convolution For Sequential Datacited by 117
  8. 2021Rethinking Architecture Selection in Differentiable NAScited by 92
  9. 2021HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmarkcited by 83
  10. 2020Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarkscited by 67
  11. 2020NAS-Bench-NLP: Neural Architecture Search Benchmark for Natural Language Processingcited by 60
  12. 2021Gated Transformer Networks for Multivariate Time Series Classificationcited by 58
  13. 2020Uncertainty in Gradient Boosting via Ensemblescited by 56
  14. 2022HYDRA: Competing convolutional kernels for fast and accurate time series classificationcited by 53
  15. 2020AutoGAN-Distiller: Searching to Compress Generative Adversarial Networkscited by 50
  16. 2020A Study on Encodings for Neural Architecture Searchcited by 37
  17. 2022Foundation Transformerscited by 19
  18. 2019TextNAS: A Neural Architecture Search Space tailored for Text Representationcited by 16
  19. 2021Trilevel Neural Architecture Search for Efficient Single Image Super-Resolutioncited by 15
  20. 2022Knowledge Distillation: Bad Models Can Be Good Role Modelscited by 12
  21. 2020Multi-fidelity Neural Architecture Search with Knowledge Distillationcited by 9
  22. 2023Modeling Events and Interactions through Temporal Processes -- A Surveycited by 5
  23. 2020Optimizing the Neural Architecture of Reinforcement Learning Agentscited by 4
  24. 2022QuantNAS for super resolution: searching for efficient quantization-friendly architectures against quantization noisecited by 4
  25. 2019Explainable Failure Predictions with RNN Classifiers based on Time Series Datacited by 3

Built on by

Cited by year

Citing papers per year: 2024: 5; 2025: 3.

8 papers.

  1. 2024Multimodal Banking Dataset: Understanding Client Needs through Event Sequencescited by 9
  2. 2024MLEM: Generative and Contrastive Learning as Distinct Modalities for Event Sequencescited by 6
  3. 2024EBES: Easy Benchmarking for Event Sequencescited by 6
  4. 2024Uniting contrastive and generative learning for event sequences modelscited by 2
  5. 2025LATTE: Learning Aligned Transactions and Textual Embeddings for Bank Clientscited by 2
  6. 2024ILASH: A Predictive Neural Architecture Search Framework for Multi-Task Applicationscited by 0
  7. 2025Looking around you: external information enhances representations for event sequencescited by 0
  8. 2025How to model Human Actions distribution with Event Sequence Datacited by 0