Metraipolis › archive › dc_69683ccc2c63
Co2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration — arXiv:2610.21804
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21804
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:04:02.152Z
- SHA-256 of the archived text
17c5748d9e4edb2feb7e01ee810eb486378357fc4daa2431889e44ffa07a6a94- Stable URL of this page
https://metraipolis.com/documento/dc_69683ccc2c63
How to cite
Co2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration — arXiv:2610.21804 — arXiv (en), https://arxiv.org/abs/2610.21804 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69683ccc2c63 (Metraipolis archive dc_69683ccc2c63, sha256 17c5748d9e4edb2feb7e01ee810eb486378357fc4daa2431889e44ffa07a6a94)
BibTeX
@misc{dc69683ccc2c63,
title = {Co2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration — arXiv:2610.21804},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21804},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69683ccc2c63; sha256 17c5748d9e4edb2feb7e01ee810eb486378357fc4daa2431889e44ffa07a6a94},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21804. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Incremental learning (IL) aims to continually acquire new knowledge (plasticity) while retaining previously learned information (stability). However, striking a balance between plasticity and stability remains a significant challenge for intelligent systems. The human brain achieves exceptional balance, owing to various memory units that collaboratively encode and store information. Inspired by human memory mechanisms, this paper introduces an IL framework with knowledge enCoding, Consolidation, and Integration (Co2In). Co2In is designed as a bi-level memory architecture: a working memory for adaptive knowledge acquisition and a long-term memory dedicated to the persistent retention of information. The two memory modules work cooperatively during IL. The working memory first learns from new data to encode knowledge into parameters. Subsequently, Co2In performs a consolidation process to identify underlying patterns in the learned parameters and re-express them into a compact knowledge representation. Next, the knowledge representation and the identified patterns are transformed into separate network layers and integrated into the long-term memory. These designs empower Co2In to accumulate knowledge with high plasticity and stability. We evaluate Co2In on CIFAR-10, CIFAR-100, and Tiny-ImageNet under exemplar-free Class-IL and Task-IL settings. Experimental results show that Co2In achieves state-of-the-art performance with efficient memory consumption. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.21804 — 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 2026-10-16T08:44:17.791Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).