Stable Unsupervised Continual Chunking with Sheaf SyncMap
Mirrored from arXiv — Machine Learning for archival readability. Support the source by reading on the original site.
Computer Science > Machine Learning
Title:Stable Unsupervised Continual Chunking with Sheaf SyncMap
Abstract:Unsupervised Continual chunking is a fundamental problem in machine learning and neuroscience, where the goal is to identify groups of states that frequently co-occur in temporal sequences. A key challenge is to form accurate chunks while maintaining their stability over time. In this work, we propose sheaf regularization to reduce local inconsistencies in Decentralized SyncMap, a self-organizing system, and thereby stabilize its chunking dynamics. We introduce a radial sheaf structure that penalizes distance-dependent radial motion between pairs of variables. Experimental results show that the proposed method achieves the highest normalized mutual information (NMI) among the evaluated SyncMap variants on 12 of 18 probabilistic Continual General Chunking Problem (CGCP) graphs with two-state memory and on 17 of 18 graphs with dynamic memory. In the sequential adaptation experiment, Sheaf SyncMap also achieves high NMI after shifts in the input distribution, indicating that it can adapt to new knowledge while avoiding the negative transfer commonly observed in modern machine learning systems such as neural networks.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.25143 [cs.LG] |
| (or arXiv:2609.25143v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.25143
arXiv-issued DOI via DataCite
|
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
References & Citations
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
More from arXiv — Machine Learning
-
Federating Quantum and Classical Computing: A Privacy-Preserving Hybrid Approach
Sep 23
-
Entropy Can Flow, or It Can Guide. Be Entropy. LEDFlow: Introducing Entropy-guided Generation Order into Uniform Discrete Flow
Sep 23
-
The Probabilistic Structure of Large Language Models
Sep 23
-
Brain-Inspired Hierarchical Modularity for General Continual Learning
Sep 23
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.