NEST is an unsupervised framework that learns a single embedding encoding coarse‑to‑fine cluster structure, optimizing clustering and separation across nested prefix subspaces. The method uses rank and within‑cluster regularization to prevent collapse, and distances in the embedding align more closely with the true hierarchy than the input distances, even though the hierarchy is not provided during training. Experiments on synthetic, vision, text, and single‑cell data show that NEST can recover multiscale structure given only the number of clusters per level, demonstrating its ability to discover multiscale organization in real‑world representations.
arXiv:2509. 03373v2 Announce Type: replace Abstract: Dimensionality reduction methods such as t-SNE and UMAP are popular methods for visualizing data with a potential (latent) clustered structure.
arXiv:2606. 13007v1 Announce Type: cross Abstract: Clustering is fundamental to scRNA-seq analysis, serving as a cornerstone for identifying cell populations and resolving tissue heterogeneity.
arXiv:2605. 28209v2 Announce Type: replace Abstract: Graph clustering is essential in graph analysis for revealing structural patterns and node communities.
The paper examines whether Deep Embedded Clustering (DEC) truly overcomes the fundamental limitations of k‑means clustering, such as handling clusters of arbitrary shapes, varied sizes, and densities. Through analysis, it finds that DEC does not exploit the underlying data distribution and therefore fails to address these limitations. Instead, a non‑deep learning approach that leverages distributional information of clusters can achieve the intended goals of deep clustering.
arXiv:2606. 02172v1 Announce Type: new Abstract: Learning discriminative visual representations from distributed, heterogeneous data is a fundamental challenge in Federated Learning (FL).
arXiv:2607. 00620v1 Announce Type: cross Abstract: Generalized Category Discovery (GCD) aims to recognize known classes while autonomously discovering novel ones in open-world settings.
The paper introduces a selective inference framework tailored for deep clustering that uses a fixed pretrained encoder to map high‑dimensional data into a latent space before clustering. It addresses the complex selection bias arising from the nonlinear transformation and offers a computationally tractable method to perform valid statistical tests on cluster differences. Experiments on synthetic data show controlled Type I error and higher power compared to conservative baselines, while genomic case studies demonstrate the ability to uncover significant cluster differences while properly accounting for selection bias.
arXiv:2606. 12077v1 Announce Type: new Abstract: Time-series clustering remains challenging due to the inherent trade-off between clustering effectiveness and computational efficiency.
The paper introduces FedDCN, a federated deep clustering network that jointly optimizes reconstruction and clustering losses for high‑dimensional, heterogeneous data. It addresses challenges of non‑IID client data by generating synthetic augmentations and applying geometric regularization to align latent spaces. Experiments show the method’s effectiveness under both IID and non‑IID settings, and the authors outline future research directions.
arXiv:2605. 29987v2 Announce Type: replace Abstract: Although multi-scales representation learning enables elastic-dimension embeddings, nested subspaces often suffer from dimensional redundancy and spectral collapse.
The paper introduces ClusterMixer, a token mixer based on hierarchical clustering in hyperbolic space, designed to be transparent and interpretable. It forms the core of a new vision backbone called HCFormer, which incorporates multiple clustering strategies to maintain strong performance. Experiments show HCFormer surpasses existing backbones on tasks such as image classification, object detection, instance segmentation, and semantic segmentation.
The paper introduces CoCo, a conjoint framework for deep graph clustering that emphasizes compactness and consistency in node representations. CoCo uses graph convolutional filters to learn robust embeddings from both local and global views, then encodes them into low‑rank compact embeddings to reduce redundancy and noise. A consistency learning strategy further enriches node semantics, enabling knowledge transfer between perspectives and yielding superior performance over state‑of‑the‑art methods on multiple datasets.