# Adaptive Online Incremental Learning for Evolving Data Streams

arXiv: https://arxiv.org/abs/2201.01633 · HTML: https://mlsanity.com/paper/2201.01633/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 53 references that are in the map.
- First posted on arXiv 5 Jan 2022.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [A Structured Self-attentive Sentence Embedding](https://mlsanity.com/paper/1703.03130/) (2017)
- [Online Deep Learning: Learning Deep Neural Networks on the Fly](https://mlsanity.com/paper/1711.03705/) (2017)
- [Spiking Neural Networks and Online Learning: An Overview and Perspectives](https://mlsanity.com/paper/1908.08019/) (2019)
- [DEVDAN: Deep Evolving Denoising Autoencoder](https://mlsanity.com/paper/1910.04062/) (2019)
- [Autonomous Deep Learning: Continual Learning Approach for Dynamic Environments](https://mlsanity.com/paper/1810.07348/) (2018)
- [ATL: Autonomous Knowledge Transfer from Many Streaming Processes](https://mlsanity.com/paper/1910.03434/) (2019)
- [Analyzing Business Process Anomalies Using Autoencoders](https://mlsanity.com/paper/1803.01092/) (2018)
- [An Incremental Construction of Deep Neuro Fuzzy System for Continual Learning of Non-stationary Data Streams](https://mlsanity.com/paper/1808.08517/) (2018)

## Built on by (most cited first, 11 of 11)

- [From Concept Drift to Model Degradation: An Overview on Performance-Aware Drift Detectors](https://mlsanity.com/paper/2203.11070/) (2022)
- [Mixture of Experts (MoE): A Big Data Perspective](https://mlsanity.com/paper/2501.16352/) (2025)
- [Untargeted White-box Adversarial Attack with Heuristic Defence Methods in Real-time Deep Learning based Network Intrusion Detection System](https://mlsanity.com/paper/2310.03334/) (2023)
- [CAdam: Confidence-Based Optimization for Online Learning](https://mlsanity.com/paper/2411.19647/) (2024)
- [Incremental Online Learning of Randomized Neural Network with Forward Regularization](https://mlsanity.com/paper/2412.13096/) (2024)
- [Domain Knowledge-Enhanced LLMs for Fraud and Concept Drift Detection](https://mlsanity.com/paper/2506.21443/) (2025)
- [Learning Unbiased Cluster Descriptors for Interpretable Imbalanced Concept Drift Detection](https://mlsanity.com/paper/2603.06757/) (2026)
- [Joint Detection of Fraud and Concept Drift inOnline Conversations with LLM-Assisted Judgment](https://mlsanity.com/paper/2505.07852/) (2025)
- [Adaptive Learning for Service Monitoring Data](https://mlsanity.com/paper/2208.12281/) (2022)
- [Logit-Origin Centering for Singleton Test-Time Adaptation](https://mlsanity.com/paper/2608.01074/) (2026)
- [Concept Drift Detection and Adaptive Retraining of Malware Classification Models](https://mlsanity.com/paper/2608.13465/) (2026)

## Abstract (arXiv)

Recent years have witnessed growing interests in online incremental learning. However, there are three major challenges in this area. The first major difficulty is concept drift, that is, the probability distribution in the streaming data would change as the data arrives. The second major difficulty is catastrophic forgetting, that is, forgetting what we have learned before when learning new knowledge. The last one we often ignore is the learning of the latent representation. Only good latent representation can improve the prediction accuracy of the model. Our research builds on this observation and attempts to overcome these difficulties. To this end, we propose an Adaptive Online Incremental Learning for evolving data streams (AOIL). We use auto-encoder with the memory module, on the one hand, we obtained the latent features of the input, on the other hand, according to the reconstruction loss of the auto-encoder with memory module, we could successfully detect the existence of concept drift and trigger the update mechanism, adjust the model parameters in time. In addition, we divide features, which are derived from the activation of the hidden layers, into two parts, which are used to extract the common and private features respectively. By means of this approach, the model could learn the private features of the new coming instances, but do not forget what we have learned in the past (shared features), which reduces the occurrence of catastrophic forgetting. At the same time, to get the fusion feature vector we use the self-attention mechanism to effectively fuse the extracted features, which further improved the latent representation learning.