English

Monitoring Neural Training with Topology: A Footprint-Predictable Collapse Index

Machine Learning 2026-05-01 v1

Abstract

Representational collapse, where embeddings become anisotropic and lose multi-scale structure, can erode downstream performance long before performance metrics react. We propose an online, topology-aware monitor for evolving neural representations that couples Modular Morse Homology Maintenance (MMHM) with a composite Collapse Index (CI). Instead of rebuilding complexes each epoch, we apply sparse edits at a fixed scale and maintain a discrete Morse matching, yielding fast, incremental updates. Across LLM fine-tuning and temporal KGE training, CI provides a low-latency early-warning signal suitable for in-training interventions. Code and experimental scripts will be released publicly

Keywords

Cite

@article{arxiv.2604.26984,
  title  = {Monitoring Neural Training with Topology: A Footprint-Predictable Collapse Index},
  author = {Alexander Kalinowski},
  journal= {arXiv preprint arXiv:2604.26984},
  year   = {2026}
}
R2 v1 2026-07-01T12:41:59.550Z