Self-Regulated Neurogenesis for Online Data-Incremental Learning

Murat Onur Yildirim, Elif Ceren Gok Yildirim, Decebal Constantin Mocanu, Joaquin Vanschoren
Proceedings of The 4th Conference on Lifelong Learning Agents, PMLR 330:657-671, 2026.

Abstract

Neural networks often struggle with catastrophic forgetting when learning sequences of tasks or data streams, unlike humans who can continuously learn and consolidate new concepts even in the absence of explicit cues. Online data-incremental learning seeks to emulate this capability by processing each sample only once, without having access to task or stream cues at any point in time since this is more realistic compared to offline setups, where all data from novel class(es) is assumed to be readily available. However, existing methods typically rely on storing the subsets of data in memory or expanding the initial model architecture, resulting in significant computational overhead. Drawing inspiration from ‘self-regulated neurogenesis’—brain’s mechanism for creating specialized regions or circuits for distinct functions—we propose a novel approach SERENA which encodes each concept in a specialized network path called ‘concept cell’, integrated into a single over-parameterized network. Once a concept is learned, its corresponding concept cell is frozen, effectively preventing the forgetting of previously acquired information. Furthermore, we introduce two new continual learning scenarios that more closely reflect real-world conditions, characterized by gradually changing sample sizes. Experimental results show that our method not only establishes new state-of-the-art results across ten benchmarks but also remarkably surpasses offline supervised batch learning performance. The code is available at https://github.com/muratonuryildirim/serena.

Cite this Paper

BibTeX
@InProceedings{pmlr-v330-yildirim26a, title = {Self-Regulated Neurogenesis for Online Data-Incremental Learning}, author = {Yildirim, Murat Onur and Yildirim, Elif Ceren Gok and Mocanu, Decebal Constantin and Vanschoren, Joaquin}, booktitle = {Proceedings of The 4th Conference on Lifelong Learning Agents}, pages = {657--671}, year = {2026}, editor = {Chandar, Sarath and Pascanu, Razvan and Eaton, Eric and Liu, Bing and Mahmood, Rupam and Rannen-Triki, Amal}, volume = {330}, series = {Proceedings of Machine Learning Research}, month = {11--14 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v330/main/assets/yildirim26a/yildirim26a.pdf}, url = {https://proceedings.mlr.press/v330/yildirim26a.html}, abstract = {Neural networks often struggle with catastrophic forgetting when learning sequences of tasks or data streams, unlike humans who can continuously learn and consolidate new concepts even in the absence of explicit cues. Online data-incremental learning seeks to emulate this capability by processing each sample only once, without having access to task or stream cues at any point in time since this is more realistic compared to offline setups, where all data from novel class(es) is assumed to be readily available. However, existing methods typically rely on storing the subsets of data in memory or expanding the initial model architecture, resulting in significant computational overhead. Drawing inspiration from ‘self-regulated neurogenesis’—brain’s mechanism for creating specialized regions or circuits for distinct functions—we propose a novel approach SERENA which encodes each concept in a specialized network path called ‘concept cell’, integrated into a single over-parameterized network. Once a concept is learned, its corresponding concept cell is frozen, effectively preventing the forgetting of previously acquired information. Furthermore, we introduce two new continual learning scenarios that more closely reflect real-world conditions, characterized by gradually changing sample sizes. Experimental results show that our method not only establishes new state-of-the-art results across ten benchmarks but also remarkably surpasses offline supervised batch learning performance. The code is available at https://github.com/muratonuryildirim/serena.} }
Endnote
%0 Conference Paper %T Self-Regulated Neurogenesis for Online Data-Incremental Learning %A Murat Onur Yildirim %A Elif Ceren Gok Yildirim %A Decebal Constantin Mocanu %A Joaquin Vanschoren %B Proceedings of The 4th Conference on Lifelong Learning Agents %C Proceedings of Machine Learning Research %D 2026 %E Sarath Chandar %E Razvan Pascanu %E Eric Eaton %E Bing Liu %E Rupam Mahmood %E Amal Rannen-Triki %F pmlr-v330-yildirim26a %I PMLR %P 657--671 %U https://proceedings.mlr.press/v330/yildirim26a.html %V 330 %X Neural networks often struggle with catastrophic forgetting when learning sequences of tasks or data streams, unlike humans who can continuously learn and consolidate new concepts even in the absence of explicit cues. Online data-incremental learning seeks to emulate this capability by processing each sample only once, without having access to task or stream cues at any point in time since this is more realistic compared to offline setups, where all data from novel class(es) is assumed to be readily available. However, existing methods typically rely on storing the subsets of data in memory or expanding the initial model architecture, resulting in significant computational overhead. Drawing inspiration from ‘self-regulated neurogenesis’—brain’s mechanism for creating specialized regions or circuits for distinct functions—we propose a novel approach SERENA which encodes each concept in a specialized network path called ‘concept cell’, integrated into a single over-parameterized network. Once a concept is learned, its corresponding concept cell is frozen, effectively preventing the forgetting of previously acquired information. Furthermore, we introduce two new continual learning scenarios that more closely reflect real-world conditions, characterized by gradually changing sample sizes. Experimental results show that our method not only establishes new state-of-the-art results across ten benchmarks but also remarkably surpasses offline supervised batch learning performance. The code is available at https://github.com/muratonuryildirim/serena.
APA
Yildirim, M.O., Yildirim, E.C.G., Mocanu, D.C. & Vanschoren, J.. (2026). Self-Regulated Neurogenesis for Online Data-Incremental Learning. Proceedings of The 4th Conference on Lifelong Learning Agents, in Proceedings of Machine Learning Research 330:657-671 Available from https://proceedings.mlr.press/v330/yildirim26a.html.

Related Material