Skip to main content

2020 | OriginalPaper | Buchkapitel

Continual Rare-Class Recognition with Emerging Novel Subclasses

verfasst von : Hung Nguyen, Xuejian Wang, Leman Akoglu

Erschienen in: Machine Learning and Knowledge Discovery in Databases

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Given a labeled dataset that contains a rare (or minority) class of of-interest instances, as well as a large class of instances that are not of interest, how can we learn to recognize future of-interest instances over a continuous stream? We introduce RaRecognize, which (i) estimates a general decision boundary between the rare and the majority class, (ii) learns to recognize individual rare subclasses that exist within the training data, as well as (iii) flags instances from previously unseen rare subclasses as newly emerging. The learner in (i) is general in the sense that by construction it is dissimilar to the specialized learners in (ii), thus distinguishes minority from the majority without overly tuning to what is seen in the training data. Thanks to this generality, RaRecognize ignores all future instances that it labels as majority and recognizes the recurrent as well as emerging rare subclasses only. This saves effort at test time as well as ensures that the model size grows moderately over time as it only maintains specialized minority learners. Through extensive experiments, we show that RaRecognize outperforms state-of-the art baselines on three real-world datasets that contain corporate-risk and disaster documents as rare classes.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Chen, Z., Liu, B.: Lifelong machine learning. Synth. Lect. Artif. Intell. Mach. Learn. 10(3), 1–145 (2016)CrossRef Chen, Z., Liu, B.: Lifelong machine learning. Synth. Lect. Artif. Intell. Mach. Learn. 10(3), 1–145 (2016)CrossRef
2.
Zurück zum Zitat French, R.: Catastrophic forgetting in connectionist networks. Trends Cogn. Sci. 3, 128–135 (1999)CrossRef French, R.: Catastrophic forgetting in connectionist networks. Trends Cogn. Sci. 3, 128–135 (1999)CrossRef
3.
Zurück zum Zitat Kemker, R., Kanan, C.: Fearnet: brain-inspired model for incremental learning. In ICLR (2018) Kemker, R., Kanan, C.: Fearnet: brain-inspired model for incremental learning. In ICLR (2018)
4.
Zurück zum Zitat Kim, Y.: Convolutional neural networks for sentence classification. In: EMNLP (2014) Kim, Y.: Convolutional neural networks for sentence classification. In: EMNLP (2014)
5.
Zurück zum Zitat Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. PNAS 114(13), 3521–3526 (2017)MathSciNetCrossRef Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. PNAS 114(13), 3521–3526 (2017)MathSciNetCrossRef
6.
Zurück zum Zitat Le, Q.V., Mikolov, T.: Distributed representations of sentences and documents. ICML 14, 1188–1196 (2014) Le, Q.V., Mikolov, T.: Distributed representations of sentences and documents. ICML 14, 1188–1196 (2014)
7.
Zurück zum Zitat Lee, S.-W., Kim, J.-H., Jun, J., Ha, J.-W., Zhang, B.-T.: Overcoming catastrophic forgetting by incremental moment matching. In NeurlPS, pp. 4652–4662 (2017) Lee, S.-W., Kim, J.-H., Jun, J., Ha, J.-W., Zhang, B.-T.: Overcoming catastrophic forgetting by incremental moment matching. In NeurlPS, pp. 4652–4662 (2017)
8.
Zurück zum Zitat Mu, X., Ting, K.M., Zhou, Z.-H.: Classification under streaming emerging new classes: a solution using completely-random trees. IEEE TKDE 29(8), 1605–1618 (2017) Mu, X., Ting, K.M., Zhou, Z.-H.: Classification under streaming emerging new classes: a solution using completely-random trees. IEEE TKDE 29(8), 1605–1618 (2017)
9.
Zurück zum Zitat Mu, X., Zhu, F., Du, J., Lim, E.-P., Zhou, Z.-H.: Streaming classification with emerging new class by class matrix sketching. In: AAAI (2017) Mu, X., Zhu, F., Du, J., Lim, E.-P., Zhou, Z.-H.: Streaming classification with emerging new class by class matrix sketching. In: AAAI (2017)
10.
Zurück zum Zitat Nguyen, H., Wang, X., Akoglu, L.: Continual rare-class recognition with emerging novel subclasses. arXiv preprint (2019) Nguyen, H., Wang, X., Akoglu, L.: Continual rare-class recognition with emerging novel subclasses. arXiv preprint (2019)
11.
Zurück zum Zitat Rebuffi, S.-A., Kolesnikov, A., Sperl, G., Lampert, C.H.: ICARL: Incremental classifier and representation learning. In: CVPR, pp. 2001–2010 (2017) Rebuffi, S.-A., Kolesnikov, A., Sperl, G., Lampert, C.H.: ICARL: Incremental classifier and representation learning. In: CVPR, pp. 2001–2010 (2017)
12.
Zurück zum Zitat Shin, H., Lee, J.K., Kim, J., Kim, J.: Continual learning with deep generative replay. In: NeurlPS, pp. 2990–2999 (2017) Shin, H., Lee, J.K., Kim, J., Kim, J.: Continual learning with deep generative replay. In: NeurlPS, pp. 2990–2999 (2017)
13.
Zurück zum Zitat Shu, L., Xu, H., Liu, B.: Doc: deep open classification of text documents. In: EMNLP (2017) Shu, L., Xu, H., Liu, B.: Doc: deep open classification of text documents. In: EMNLP (2017)
14.
15.
Zurück zum Zitat Siffer, A., Fouque, P.-A., Termier, A., Largouet, C.: Anomaly detection in streams with extreme value theory. In: KDD, pp. 1067–1075. ACM (2017) Siffer, A., Fouque, P.-A., Termier, A., Largouet, C.: Anomaly detection in streams with extreme value theory. In: KDD, pp. 1067–1075. ACM (2017)
16.
Zurück zum Zitat Xu, H., Liu, B., Shu, L., Yu, P.: Open-world learning and application to product classification. In: WWW (2019) Xu, H., Liu, B., Shu, L., Yu, P.: Open-world learning and application to product classification. In: WWW (2019)
17.
Zurück zum Zitat Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: NeurlPS, pp. 649–657 (2015) Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: NeurlPS, pp. 649–657 (2015)
Metadaten
Titel
Continual Rare-Class Recognition with Emerging Novel Subclasses
verfasst von
Hung Nguyen
Xuejian Wang
Leman Akoglu
Copyright-Jahr
2020
DOI
https://doi.org/10.1007/978-3-030-46147-8_2