# Continual Learning in Predictive Autoscaling

arXiv: https://arxiv.org/abs/2307.15941 · HTML: https://mlsanity.com/paper/2307.15941/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 29 Jul 2023.

## Builds on (most cited first, 19 of 19)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Task-Free Continual Learning](https://mlsanity.com/paper/1812.03596/) (2018)
- [REMIND Your Neural Network to Prevent Catastrophic Forgetting](https://mlsanity.com/paper/1910.02509/) (2019)
- [Delving into Deep Imbalanced Regression](https://mlsanity.com/paper/2102.09554/) (2021)
- [RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression](https://mlsanity.com/paper/2205.15236/) (2022)
- [Information-theoretic Online Memory Selection for Continual Learning](https://mlsanity.com/paper/2204.04763/) (2022)
- [Distilling Knowledge From a Deep Pose Regressor Network](https://mlsanity.com/paper/1908.00858/) (2019)
- [CLeaR: An Adaptive Continual Learning Framework for Regression Tasks](https://mlsanity.com/paper/2101.00926/) (2021)
- [A Meta Reinforcement Learning Approach for Predictive Autoscaling in the Cloud](https://mlsanity.com/paper/2205.15795/) (2022)
- [pTSE: A Multi-model Ensemble Method for Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2305.11304/) (2023)
- [An Efficient Method of Training Small Models for Regression Problems with Knowledge Distillation](https://mlsanity.com/paper/2002.12597/) (2020)
- [Continual Causal Inference with Incremental Observational Data](https://mlsanity.com/paper/2303.01775/) (2023)
- [Automatic Deduction Path Learning via Reinforcement Learning with Environmental Correction](https://mlsanity.com/paper/2306.10083/) (2023)

## Built on by (most cited first, 4 of 4)

- [Prompt-augmented Temporal Point Process for Streaming Event Sequence](https://mlsanity.com/paper/2310.04993/) (2023)
- [ASAP: Unsupervised Post-training with Label Distribution Shift Adaptive Learning Rate](https://mlsanity.com/paper/2508.13445/) (2025)
- [Deep Optimal Timing Strategies for Time Series](https://mlsanity.com/paper/2310.05479/) (2023)
- [OASIS: Open-world Adaptive Self-supervised and Imbalanced-aware System](https://mlsanity.com/paper/2508.16656/) (2025)

## Abstract (arXiv)

Predictive Autoscaling is used to forecast the workloads of servers and prepare the resources in advance to ensure service level objectives (SLOs) in dynamic cloud environments. However, in practice, its prediction task often suffers from performance degradation under abnormal traffics caused by external events (such as sales promotional activities and applications re-configurations), for which a common solution is to re-train the model with data of a long historical period, but at the expense of high computational and storage costs. To better address this problem, we propose a replay-based continual learning method, i.e., Density-based Memory Selection and Hint-based Network Learning Model (DMSHM), using only a small part of the historical log to achieve accurate predictions. First, we discover the phenomenon of sample overlap when applying replay-based continual learning in prediction tasks. In order to surmount this challenge and effectively integrate new sample distribution, we propose a density-based sample selection strategy that utilizes kernel density estimation to calculate sample density as a reference to compute sample weight, and employs weight sampling to construct a new memory set. Then we implement hint-based network learning based on hint representation to optimize the parameters. Finally, we conduct experiments on public and industrial datasets to demonstrate that our proposed method outperforms state-of-the-art continual learning methods in terms of memory capacity and prediction accuracy. Furthermore, we demonstrate remarkable practicability of DMSHM in real industrial applications.