C-SMOTE: Continuous Synthetic Minority Oversampling for Evolving Data Streams

The world is constantly changing, and so are the massive amount of data produced. However, only a few studies deal with online class imbalance learning that combines the challenges of class-imbalanced data streams and concept drift. In this paper, we propose the very fast continuous synthetic minority oversampling technique (VFC-SMOTE). It is a novel meta-strategy to be prepended to any streaming machine learning classification algorithm aiming at oversampling the minority class using a new version of Smote and Borderline-Smote inspired by Data Sketching. We benchmarked VFC-SMOTE pipelines on synthetic and real data streams containing different concept drifts, imbalance levels, and class distributions. We bring statistical evidence that VFC-SMOTE pipelines learn models whose minority class performances are better than state-of-the-art. Moreover, we analyze the time/memory consumption and the concept drift recovery speed.

show abstract

“…C-SMOTE (Bernardo et al 2020b) is a meta-strategy similar to VFC-SMOTE, designed to be prepended to any SML-techniques. It is inspired by Smote.…”

Section: Related Workmentioning

confidence: 99%

VFC-SMOTE: very fast continuous synthetic minority oversampling for evolving data streams

Bernardo

Valle

2021

Data Min Knowl Disc

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [35], the authors convert classical class imbalance boosting methods such as AdaC2 and RUSBoost to online learners with the help of ADWIN change detector. A recently proposed method [2], employs an online SMOTE strategy which resamples the minority class from a sliding window and afterwards it updates an adaptive random forest ensemble equipped with ADWIN for change detection.…”

Section: Related Workmentioning

confidence: 99%

“…This work is an extension of our previous work [23]. The major changes include: i) modifying the distribution update part by also reducing the majority weights, ii) extending FABBOO to facilitate another parity-based notion of fairness, namely predictive equality, iii) adding two real-world datasets to the experimental evaluation, iv) adding a recently published state-of-the-art imbalance-aware stream classifier [2] for comparison, iv) providing a detailed analysis w.r.t FABBOO's hyper-parameters selection.…”

mentioning

confidence: 99%

Online Fairness-Aware Learning with Imbalanced Data Streams

Iosifidis,

Zhang,

Ntoutsi

2021

Preprint

View full text Add to dashboard Cite

Data-driven learning algorithms are employed in many online applications, in which data become available over time, like network monitoring, stock price prediction, job applications, etc. The underlying data distribution might evolve over time calling for model adaptation as new instances arrive and old instances become obsolete. In such dynamic environments, the so-called data streams, fairness-aware learning cannot be considered as a one-off requirement, but rather it should comprise a continual requirement over the stream. Recent fairness-aware stream classifiers ignore the problem of class imbalance, which manifests in many real-life applications, and mitigate discrimination mainly because they "reject" minority instances at large due to their inability to effectively learn all classes.In this work, we propose FABBOO, an online fairness-aware approach that maintains a valid and fair classifier over the stream. FABBOO is an online boosting approach that changes the training distribution in an online fashion by monitoring stream's class imbalance and tweaks its decision boundary to mitigate discriminatory outcomes over the stream. Experiments on 8 real-world and 1 synthetic datasets from different domains with varying class imbalance demonstrate the superiority of our method over state-of-the-art fairnessaware stream approaches with a range (relative) increase [11.2%-14.2%] in balanced accuracy, [22.6%-31.8%] in gmean, [42.5%-49.6%] in recall, [14.3%-25.7%] in kappa and [89.4%-96.6%] in statistical parity (fairness).

show abstract

“…This section recalls the C-SMOTE description, inspired by SMOTE, originally presented in [4]. C-SMOTE is designed to rebalance an imbalanced data stream and, as Fig.…”

Section: C-smotementioning

confidence: 99%

“…To address this problem, we applied our novel C-SMOTE [4] SML meta-strategy, inspired by SMOTE [5] class rebalancing algorithm. Considering that in literature there are SML algorithms natively able to rebalance streams in presence of concept drifts (let's denote them with SML+) and algorithms unable to do so (say, SML-), we formulated the following research questions:…”

Section: Introductionmentioning

confidence: 99%

Predict COVID-19 Spreading With C-SMOTE

Bernardo

Valle

2021

Bus. Inf. Sys.

Self Cite

View full text Add to dashboard Cite

Data continuously gathered monitoring the spreading of the COVID-19 pandemic form an unbounded flow of data. Accurately forecasting if the infections will increase or decrease has a high impact, but it is challenging because the pandemic spreads and contracts periodically. Technically, the flow of data is said to be imbalanced and subject to concept drifts because signs of decrements are the minority class during the spreading periods, while they become the majority class in the contraction periods and the other way round. In this paper, we propose a case study applying the Continuous Synthetic Minority Oversampling Technique (C-SMOTE), a novel meta-strategy to pipeline with Streaming Machine Learning (SML) classification algorithms, to forecast the COVID-19 pandemic trend. Benchmarking SML pipelinesthat use C-SMOTE against state-of-the-art methods on a COVID-19 dataset, we bring statistical evidence that models learned using C-SMOTE are better.

show abstract

C-SMOTE: Continuous Synthetic Minority Oversampling for Evolving Data Streams

Cited by 29 publications

References 19 publications

VFC-SMOTE: very fast continuous synthetic minority oversampling for evolving data streams

VFC-SMOTE: very fast continuous synthetic minority oversampling for evolving data streams

Online Fairness-Aware Learning with Imbalanced Data Streams

Predict COVID-19 Spreading With C-SMOTE

Contact Info

Product

Resources

About