arXiv Machine Learning
Stable Unsupervised Continual Chunking with Sheaf SyncMap
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 1
CLIMB: Centroid-Based Hierarchical Memory for Online Continual Self-Supervised Learning
arXiv:2606. 31275v1 Announce Type: cross Abstract: Online Continual Self-Supervised Learning (OCSSL) aims to learn representations from a continuous stream of unlabeled data, without knowledge of task boundaries and under memory constraints.
arXiv AI
Aug 20
Forgetting, plasticity, and co-observation: a third facet of continual learning
The paper argues that catastrophic forgetting and loss of plasticity alone cannot explain why naive sequential training underperforms offline joint training. It introduces data co-observation as a third factor, showing that observing training data together consistently improves performance across supervised and self-supervised settings. The study also reinterprets common continual learning methods, suggesting that memory replay’s success stems from restoring co-observation benefits rather than merely mitigating forgetting.
arXiv Machine Learning
Jul 2
SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport
arXiv:2607. 00377v1 Announce Type: new Abstract: Self-supervised Continual Graph Learning (CGL) aims to successively learn from a graph sequence with different tasks without label supervision - a paradigm that has attracted widespread attention.
arXiv Machine Learning
Jun 30
DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts
arXiv:2605. 12998v3 Announce Type: replace Abstract: Continual graph learning (CGL) aims to learn from dynamically evolving graphs while mitigating catastrophic forgetting.
arXiv AI
Sep 7
MePo++: Unifying Representation Refinement and Reconciliation for General Continual Learning
MePo++ is a post‑training framework designed for general continual learning (GCL) that unifies representation refinement and reconciliation. It introduces MetaPrep, which enhances representation plasticity via unsupervised meta‑refinement on pseudo continual sequences, and StreamAlign, which maintains stability by reconciling online features with a stable pretrained geometry. Experiments across various pretrained models, datasets, and continual learning baselines show that MePo++ consistently improves performance in PTM‑based GCL.
arXiv Machine Learning
Jul 14
CA-DGCL: Dynamic Graph Continual Learning via Condensation and Attachment
arXiv:2607. 11112v1 Announce Type: new Abstract: Dynamic graph continual learning (DGCL) is an effective manner for handling catastrophic forgetting in dynamic graphs.