# CoSeNet: A Novel Approach for Optimal Segmentation of Correlation Matrices

arXiv: https://arxiv.org/abs/2512.21000 · HTML: https://mlsanity.com/paper/2512.21000/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 65 references that are in the map.
- First posted on arXiv 24 Dec 2025.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Deep clustering: Discriminative embeddings for segmentation and separation](https://mlsanity.com/paper/1508.04306/) (2015)
- [Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization](https://mlsanity.com/paper/1710.05179/) (2017)
- [Structured Sparse Subspace Clustering: A Joint Affinity Learning and Subspace Clustering Framework](https://mlsanity.com/paper/1610.05211/) (2016)
- [Hierarchical Correlation Clustering and Tree Preserving Embedding](https://mlsanity.com/paper/2002.07756/) (2020)
- [Modularity maximization as a flexible and generic framework for brain network exploratory analysis](https://mlsanity.com/paper/2106.15428/) (2021)

## Abstract (arXiv)

In this paper, we propose a novel approach for the optimal identification of correlated segments in noisy correlation matrices. The proposed model is known as CoSeNet (Correlation Seg-mentation Network) and is based on a four-layer algorithmic architecture that includes several processing layers: input, formatting, re-scaling, and segmentation layer. The proposed model can effectively identify correlated segments in such matrices, better than previous approaches for similar problems. Internally, the proposed model utilizes an overlapping technique and uses pre-trained Machine Learning (ML) algorithms, which makes it robust and generalizable. CoSeNet approach also includes a method that optimizes the parameters of the re-scaling layer using a heuristic algorithm and fitness based on a Window Difference-based metric. The output of the model is a binary noise-free matrix representing optimal segmentation as well as its seg-mentation points and can be used in a variety of applications, obtaining compromise solutions between efficiency, memory, and speed of the proposed deployment model.