# Online Deep Learning from Doubly-Streaming Data

arXiv: https://arxiv.org/abs/2204.11793 · HTML: https://mlsanity.com/paper/2204.11793/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 101 references that are in the map.
- First posted on arXiv 25 Apr 2022.

## Builds on (most cited first, 30 of 33)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators](https://mlsanity.com/paper/1910.03193/) (2019)
- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Net2Net: Accelerating Learning via Knowledge Transfer](https://mlsanity.com/paper/1511.05641/) (2015)
- [FractalNet: Ultra-Deep Neural Networks without Residuals](https://mlsanity.com/paper/1605.07648/) (2016)
- [The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence](https://mlsanity.com/paper/2002.06177/) (2020)
- [Generalization in Deep Learning](https://mlsanity.com/paper/1710.05468/) (2017)
- [Online Meta-Learning](https://mlsanity.com/paper/1902.08438/) (2019)
- [Online Deep Learning: Learning Deep Neural Networks on the Fly](https://mlsanity.com/paper/1711.03705/) (2017)
- [Deep Forest](https://mlsanity.com/paper/1702.08835/) (2017)
- [Lifelong Learning of Graph Neural Networks for Open-World Node Classification](https://mlsanity.com/paper/2006.14422/) (2020)
- [Online mirror descent and dual averaging: keeping pace in the dynamic case](https://mlsanity.com/paper/2006.02585/) (2020)
- [Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach](https://mlsanity.com/paper/2110.04514/) (2021)
- [A Generalized Online Mirror Descent with Applications to Classification and Regression](https://mlsanity.com/paper/1304.2994/) (2013)
- [Relevant sparse codes with variational information bottleneck](https://mlsanity.com/paper/1605.07332/) (2016)
- [Learning with Feature Evolvable Streams](https://mlsanity.com/paper/1706.05259/) (2017)
- [One-Pass Learning with Incremental and Decremental Features](https://mlsanity.com/paper/1605.09082/) (2016)
- [The History of Digital Spam](https://mlsanity.com/paper/1908.06173/) (2019)
- [Adaptive and Scalable Android Malware Detection through Online Learning](https://mlsanity.com/paper/1606.07150/) (2016)
- [Prediction with Unpredictable Feature Evolution](https://mlsanity.com/paper/1904.12171/) (2019)
- [Storage Fit Learning with Feature Evolvable Streams](https://mlsanity.com/paper/2007.11280/) (2020)

## Built on by (most cited first, 2 of 2)

- [Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents](https://mlsanity.com/paper/2608.02018/) (2026)
- [Extension OL-MDISF: Online Learning from Mix-Typed, Drifted, and Incomplete Streaming Features](https://mlsanity.com/paper/2507.10594/) (2025)

## Abstract (arXiv)

This paper investigates a new online learning problem with doubly-streaming data, where the data streams are described by feature spaces that constantly evolve, with new features emerging and old features fading away. The challenges of this problem are two folds: 1) Data samples ceaselessly flowing in may carry shifted patterns over time, requiring learners to update hence adapt on-the-fly. 2) Newly emerging features are described by very few samples, resulting in weak learners that tend to make error predictions. A plausible idea to overcome the challenges is to establish relationship between the pre-and-post evolving feature spaces, so that an online learner can leverage the knowledge learned from the old features to better the learning performance on the new features. Unfortunately, this idea does not scale up to high-dimensional media streams with complex feature interplay, which suffers an tradeoff between onlineness (biasing shallow learners) and expressiveness(requiring deep learners). Motivated by this, we propose a novel OLD^3S paradigm, where a shared latent subspace is discovered to summarize information from the old and new feature spaces, building intermediate feature mapping relationship. A key trait of OLD^3S is to treat the model capacity as a learnable semantics, yields optimal model depth and parameters jointly, in accordance with the complexity and non-linearity of the input data streams in an online fashion. Both theoretical analyses and empirical studies substantiate the viability and effectiveness of our proposal.