Deep Modularity Networks with Diversity-Preserving Regularization

• URL: http://arxiv.org/abs/2501.13451v2
• Date: Mon, 03 Nov 2025 10:11:21 GMT
• Title: Deep Modularity Networks with Diversity-Preserving Regularization
• Authors: Yasmin Salehi, Dennis Giannacopoulos,
• Abstract summary: We propose Deep Modularity Networks with Diversity-Preserving Regularization (DMoN-DPR)<n>We introduce three novel regularization terms: distance-based for inter-cluster separation, variance-based for per-cluster assignment dispersion, and an assignment-entropy penalty with a small positive weight, encouraging more confident assignments gradually.<n>Our method significantly enhances label-based clustering metrics on feature-rich benchmark datasets (paired two-tailed t-test, $pleq0.05$), demonstrating the effectiveness of incorporating diversity-preserving regularizations in creating meaningful and interpretable clusters.
• Score: 2.5954303305216095
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph clustering plays a crucial role in graph representation learning but often faces challenges in achieving feature-space diversity. While Deep Modularity Networks (DMoN) leverage modularity maximization and collapse regularization to ensure structural separation, they lack explicit mechanisms for feature-space separation, assignment dispersion, and assignment-confidence control. We address this limitation by proposing Deep Modularity Networks with Diversity-Preserving Regularization (DMoN-DPR), which introduces three novel regularization terms: distance-based for inter-cluster separation, variance-based for per-cluster assignment dispersion, and an assignment-entropy penalty with a small positive weight, encouraging more confident assignments gradually. Our method significantly enhances label-based clustering metrics on feature-rich benchmark datasets (paired two-tailed t-test, $p\leq0.05$), demonstrating the effectiveness of incorporating diversity-preserving regularizations in creating meaningful and interpretable clusters.

Related papers

• Universal NP-Hardness of Clustering under General Utilities [11.62669179647184]
  We formalise the common optimisation core motivating a diverse-time computable partition utility over a finite metric space.<n>By mapping ten major paradigms -- including k-means, GMMs, DBSCAN, spectral clustering, and affinity propagation -- to the UCP framework, we demonstrate that each inherits this fundamental inability.
  arXiv  Detail & Related papers  (2026-02-27T13:08:15Z)
• Towards Uniformity and Alignment for Multimodal Representation Learning [66.87764574237532]
  We identify two conflicts in the multimodal regime, both exacerbated as the number of modalities increases.<n>We propose a principled decoupling of alignment and uniformity for multimodal representations.<n>We then provide a theoretical guarantee that our method acts as an efficient proxy for a global Hlder divergence over multiple modality distributions.
  arXiv  Detail & Related papers  (2026-02-10T08:08:07Z)
• FSCA-Net: Feature-Separated Cross-Attention Network for Robust Multi-Dataset Training [3.2658295979028753]
  We propose a unified framework that disentangles feature representations into domain-invariant and domain-specific components.<n>A novel cross-attention fusion module adaptively models interactions between these components, ensuring effective knowledge transfer.<n>Experiments on multiple crowd counting benchmarks demonstrate that FSCA-Net effectively mitigates negative transfer and achieves state-of-the-art cross-dataset generalization.
  arXiv  Detail & Related papers  (2026-02-02T02:18:48Z)
• Self-supervised Latent Space Optimization with Nebula Variational Coding [87.20343320266215]
  This paper proposes a variational inference model which leads to a clustered embedding.<n>We introduce additional variables in the latent space, called textbfnebula anchors, that guide the latent variables to form clusters during training.<n>Since each latent feature can be labeled with the closest anchor, we also propose to apply metric learning in a self-supervised way to make the separation between clusters more explicit.
  arXiv  Detail & Related papers  (2025-06-02T08:13:32Z)
• Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering Perspective [52.662463893268225]
  Self-supervised heterogeneous graph learning (SHGL) has shown promising potential in diverse scenarios.<n>Existing SHGL methods encounter two significant limitations.<n>We introduce a novel framework enhanced by rank and dual consistency constraints.
  arXiv  Detail & Related papers  (2024-12-01T09:33:20Z)
• Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation [40.17482809009576]
  We introduce a novel perspective that imparts auxiliary constraints by regulating the feature space under weak supervision. We develop a Distribution Guidance Network (DGNet), which comprises a weakly supervised learning branch and a distribution alignment branch.
  arXiv  Detail & Related papers  (2024-10-10T16:33:27Z)
• Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments [31.437047774153037]
  This paper proposes Subequivariant Hierarchical Neural Networks (SHNN) to facilitate multi-entity policy learning. SHNN first dynamically decouples the global space into local entity-level graphs via task assignment. It then leverages subequivariant message passing over the local entity-level graphs to devise local reference frames.
  arXiv  Detail & Related papers  (2024-07-17T11:37:34Z)
• Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift [44.708914058803224]
  We establish a new model-agnostic optimization framework for out-of-distribution generalization via multicalibration. We propose MC-Pseudolabel, a post-processing algorithm to achieve both extended multicalibration and out-of-distribution generalization.
  arXiv  Detail & Related papers  (2024-06-02T08:11:35Z)
• ForecastGrapher: Redefining Multivariate Time Series Forecasting with Graph Neural Networks [9.006068771300377]
  We present ForecastGrapher, a framework for capturing the intricate temporal dynamics and inter-series correlations. Our approach is underpinned by three pivotal steps: generating custom node embeddings to reflect the temporal variations within each series; constructing an adaptive adjacency matrix to encode the inter-series correlations; and thirdly, augmenting the GNNs' expressive power by diversifying the node feature distribution.
  arXiv  Detail & Related papers  (2024-05-28T10:40:20Z)
• Rethinking Clustered Federated Learning in NOMA Enhanced Wireless Networks [60.09912912343705]
  This study explores the benefits of integrating the novel clustered federated learning (CFL) approach with non-independent and identically distributed (non-IID) datasets. A detailed theoretical analysis of the generalization gap that measures the degree of non-IID in the data distribution is presented. Solutions to address the challenges posed by non-IID conditions are proposed with the analysis of the properties.
  arXiv  Detail & Related papers  (2024-03-05T17:49:09Z)
• Multi-View Clustering via Semi-non-negative Tensor Factorization [120.87318230985653]
  We develop a novel multi-view clustering based on semi-non-negative tensor factorization (Semi-NTF) Our model directly considers the between-view relationship and exploits the between-view complementary information. In addition, we provide an optimization algorithm for the proposed method and prove mathematically that the algorithm always converges to the stationary KKT point.
  arXiv  Detail & Related papers  (2023-03-29T14:54:19Z)
• FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering [4.489171618387544]
  Federated Learning (FL) is a machine learning paradigm that safeguards privacy by retaining client data on edge devices. In this paper, we identify the learning challenges posed by the simultaneous occurrence of diverse distribution shifts. We propose a novel clustering algorithm framework, dubbed as FedRC, which adheres to our proposed clustering principle.
  arXiv  Detail & Related papers  (2023-01-29T06:50:45Z)
• Deep Diversity-Enhanced Feature Representation of Hyperspectral Images [87.47202258194719]
  We rectify 3D convolution by modifying its topology to enhance the rank upper-bound. We also propose a novel diversity-aware regularization (DA-Reg) term that acts on the feature maps to maximize independence among elements. To demonstrate the superiority of the proposed Re$3$-ConvSet and DA-Reg, we apply them to various HS image processing and analysis tasks.
  arXiv  Detail & Related papers  (2023-01-15T16:19:18Z)
• Tensor-based Multi-view Spectral Clustering via Shared Latent Space [14.470859959783995]
  Multi-view Spectral Clustering (MvSC) attracts increasing attention due to diverse data sources. New method for MvSC is proposed via a shared latent space from the Restricted Kernel Machine framework.
  arXiv  Detail & Related papers  (2022-07-23T17:30:54Z)
• Consistency and Diversity induced Human Motion Segmentation [231.36289425663702]
  We propose a novel Consistency and Diversity induced human Motion (CDMS) algorithm. Our model factorizes the source and target data into distinct multi-layer feature spaces. A multi-mutual learning strategy is carried out to reduce the domain gap between the source and target data.
  arXiv  Detail & Related papers  (2022-02-10T06:23:56Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)
• Deep Attention-guided Graph Clustering with Dual Self-supervision [49.040136530379094]
  We propose a novel method, namely deep attention-guided graph clustering with dual self-supervision (DAGC) We develop a dual self-supervision solution consisting of a soft self-supervision strategy with a triplet Kullback-Leibler divergence loss and a hard self-supervision strategy with a pseudo supervision loss. Our method consistently outperforms state-of-the-art methods on six benchmark datasets.
  arXiv  Detail & Related papers  (2021-11-10T06:53:03Z)
• Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering [119.88565565454378]
  Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain. We propose a hybrid model of Structurally Regularized Deep Clustering, which integrates the regularized discriminative clustering of target data with a generative one. Our proposed H-SRDC outperforms all the existing methods under both the inductive and transductive settings.
  arXiv  Detail & Related papers  (2020-12-08T08:52:00Z)
• Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings [25.137859989323537]
  We propose an effective Unsupervised Domain Adaptation (UDA) strategy, based on a feature clustering method. We introduce two novel learning objectives to enhance the discriminative clustering performance.
  arXiv  Detail & Related papers  (2020-11-25T10:06:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.