mlsanityData to 7 Oct 2026

Aux-Drop: Handling Haphazard Inputs in Online Learning Using Auxiliary Dropouts

arXiv 2303.05155 ↗First posted 9 Mar 2023cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Many real-world applications based on online learning produce streaming data that is haphazard in nature, i.e., contains missing features, features becoming obsolete in time, the appearance of new features at later points in time and a lack of clarity on the total number of input features. These challenges make it hard to build a learnable system for such applications, and almost no work exists in deep learning that addresses this issue. In this paper, we present Aux-Drop, an auxiliary dropout regularization strategy for online learning that handles the haphazard input features in an effective manner. Aux-Drop adapts the conventional dropout regularization scheme for the haphazard input feature space ensuring that the final output is minimally impacted by the chaotic appearance of such features. It helps to prevent the co-adaptation of especially the auxiliary and base features, as well as reduces the strong dependence of the output on any of the auxiliary inputs of the model. This helps in better learning for scenarios where certain features disappear in time or when new features are to be modelled. The efficacy of Aux-Drop has been demonstrated through extensive numerical experiments on SOTA benchmarking datasets that include Italy Power Demand, HIGGS, SUSY and multiple UCI datasets. The code is available at https://github.com/Rohit102497/Aux-Drop.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 23 of its 65 references that are in the map. First posted on arXiv 9 Mar 2023.

Builds on

23 of 65 references.

References · 23

  1. 2022Generative Adversarial Networkscited by 5,603
  2. 2016Progressive Neural Networkscited by 1,332
  3. 2016Adversarial Machine Learning at Scalecited by 934
  4. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  5. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  6. 2018The UCR Time Series Archivecited by 421
  7. 2020A Brief Review of Domain Adaptationcited by 287
  8. 2014Efficient Object Localization Using Convolutional Networkscited by 226
  9. 2018Online Learning: A Comprehensive Surveycited by 203
  10. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  11. 2017Online Deep Learning: Learning Deep Neural Networks on the Flycited by 86
  12. 2015Learning with a Strong Adversarycited by 68
11 more
  1. 2022Open-environment Machine Learningcited by 48
  2. 2021Open-world Machine Learning: Applications, Challenges, and Opportunitiescited by 34
  3. 2017Learning with Feature Evolvable Streamscited by 15
  4. 2018Autonomous Deep Learning: Continual Learning Approach for Dynamic Environmentscited by 15
  5. 2018Guided Dropoutcited by 14
  6. 2016One-Pass Learning with Incremental and Decremental Featurescited by 13
  7. 2022Nonstationary data stream classification with online active learning and siamese neural networkscited by 12
  8. 2019Prediction with Unpredictable Feature Evolutioncited by 8
  9. 2020Auxiliary Network: Scalable and agile online learning for dynamic system with inconsistently available inputscited by 5
  10. 2020Evolving Metric Learning for Incremental and Decremental Featurescited by 2
  11. 2020How Does GAN-based Semi-supervised Learning Work?cited by 2

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 1.

5 papers.

  1. 2024Online Learning under Haphazard Input Conditions: A Comprehensive Review and Analysiscited by 2
  2. 2024MODL: Multilearner Online Deep Learningcited by 1
  3. 2024Hedging Is Not All You Need: A Simple Baseline for Online Learning Under Haphazard Inputscited by 1
  4. 2024packetLSTM: Dynamic LSTM Framework for Streaming Data with Varying Feature Spacecited by 0
  5. 2025Haphazard Inputs as Images in Online Learningcited by 0