Metraipolis › archive › dc_f26a609d0bad

Forgetting, plasticity, and co-observation: a third facet of continual learning — arXiv:2608.18803

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18803
License (as archived)
CC0-1.0
Archived
2026-10-18T13:45:22.334Z
SHA-256 of the archived text
5e6b9b8915c00ca01c20642fce505295f18b2854b0a2f46939c5ef69e5052540
Stable URL of this page
https://metraipolis.com/documento/dc_f26a609d0bad

How to cite

Forgetting, plasticity, and co-observation: a third facet of continual learning — arXiv:2608.18803 — arXiv (en), https://arxiv.org/abs/2608.18803 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f26a609d0bad (Metraipolis archive dc_f26a609d0bad, sha256 5e6b9b8915c00ca01c20642fce505295f18b2854b0a2f46939c5ef69e5052540)
BibTeX
@misc{dcf26a609d0bad,
  title = {Forgetting, plasticity, and co-observation: a third facet of continual learning — arXiv:2608.18803},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18803},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f26a609d0bad; sha256 5e6b9b8915c00ca01c20642fce505295f18b2854b0a2f46939c5ef69e5052540},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18803. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Efficient continual learning remains a fundamental challenge for deep neural networks. While catastrophic forgetting and loss of plasticity are widely considered the primary obstacles to overcome, we show that these two issues cannot fully explain the performance gap between naive sequential training and offline joint training. In this paper, we highlight data co-observation as a distinct factor influencing continual learning performance. By decoupling the constraints of separate data access from stability and plasticity, we systematically investigate the representational benefits gained by observing training data together. Empirically, we demonstrate a consistent performance difference between joint and separate training across both supervised and self-supervised paradigms in generic data-incremental "chunking" scenarios, whilst mitigating forgetting and controlling for plasticity. Our findings indicate that simultaneous observation of training data (co-observation) yields benefits to the learner's generalization that extend well beyond mere knowledge retention, and that this effect does not require a specific continual distribution shift. Furthermore, we contextualize prominent continual learning mechanisms through this lens: while distillation-based approaches act only as effective knowledge retention mechanisms, our results suggest that the empirical success of memory replay goes beyond the mitigation of forgetting, actively reintroducing the benefits of data co-observation into the learning process.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.18803 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T13:41:17.976Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).