Silhouette Loss: Differentiable Global Structure Learning for Deep Representations

• URL: http://arxiv.org/abs/2604.08573v1
• Date: Fri, 27 Mar 2026 12:11:47 GMT
• Title: Silhouette Loss: Differentiable Global Structure Learning for Deep Representations
• Abstract summary: We introduce Soft Silhouette Loss, a novel differentiable objective inspired by the classical silhouette coefficient from clustering analysis.<n>Our formulation evaluates each sample against all classes in the batch, providing a batch-level notion of global structure.<n>It can be seamlessly combined with cross-entropy, and is also complementary to supervised contrastive learning.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning discriminative representations is a central goal of supervised deep learning. While cross-entropy (CE) remains the dominant objective for classification, it does not explicitly enforce desirable geometric properties in the embedding space, such as intra-class compactness and inter-class separation. Existing metric learning approaches, including supervised contrastive learning (SupCon) and proxy-based methods, address this limitation by operating on pairwise or proxy-based relationships, but often increase computational cost and complexity. In this work, we introduce Soft Silhouette Loss, a novel differentiable objective inspired by the classical silhouette coefficient from clustering analysis. Unlike pairwise objectives, our formulation evaluates each sample against all classes in the batch, providing a batch-level notion of global structure. The proposed loss directly encourages samples to be closer to their own class than to competing classes, while remaining lightweight. Soft Silhouette Loss can be seamlessly combined with cross-entropy, and is also complementary to supervised contrastive learning. We propose a hybrid objective that integrates them, jointly optimizing local pairwise consistency and global cluster structure. Extensive experiments on seven diverse datasets demonstrate that: (i) augmenting CE with Soft Silhouette Loss consistently improves over CE and other metric learning baselines; (ii) the hybrid formulation outperforms SupCon alone; and (iii) the combined method achieves the best performance, improving average top-1 accuracy from 36.71% (CE) and 37.85% (SupCon2) to 39.08%, while incurring substantially lower computational overhead. These results suggest that classical clustering principles can be reinterpreted as differentiable objectives for deep learning, enabling efficient optimization of both local and global structure in representation spaces.

Related papers

• Contrastive-Collapsed Loss for Flexible and Geometrically Optimal Embeddings and Faster Convergence [0.4205692673448205]
  We introduce CoCo, a loss function aimed at learning normalized and well-structured representations.<n>We show that CoCo achieves competitive performance with state-of-the-art methods, including kernel SVM, Random Forest, dot regression, and cross-entropy-based neural networks.
  arXiv  Detail & Related papers  (2026-07-14T15:51:41Z)
• Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language Models [20.68004586002534]
  We propose cluster-aware neural collapse prompt tuning (CPT)<n>CPT enhances the discriminability of tail classes in prompt-tuned vision-language models without sacrificing generalization.<n>Experiments on 11 diverse datasets demonstrate that CPT outperforms SOTA methods.
  arXiv  Detail & Related papers  (2026-05-12T10:50:43Z)
• NDCG-Consistent Softmax Approximation with Accelerated Convergence [67.10365329542365]
  We propose novel loss formulations that align directly with ranking metrics.<n>We integrate the proposed RG losses with the highly efficient Alternating Least Squares (ALS) optimization method.<n> Empirical evaluations on real-world datasets demonstrate that our approach achieves comparable or superior ranking performance.
  arXiv  Detail & Related papers  (2025-06-11T06:59:17Z)
• LCFed: An Efficient Clustered Federated Learning Framework for Heterogeneous Data [21.341280782748278]
  Clustered federated learning (CFL) addresses the performance challenges posed by data heterogeneity in federated learning (FL)<n>Existing CFL approaches strictly limit knowledge sharing to within clusters, lacking the integration of global knowledge with intra-cluster training.<n>We propose LCFed, an efficient CFL framework to combat these challenges.
  arXiv  Detail & Related papers  (2025-01-03T14:59:48Z)
• SimO Loss: Anchor-Free Contrastive Loss for Fine-Grained Supervised Contrastive Learning [0.0]
  We introduce a novel anchor-free contrastive learning (L) method leveraging our proposed Similarity-Orthogonality (SimO) loss. Our approach minimizes a semi-metric discriminative loss function that simultaneously optimize two key objectives. We provide visualizations that demonstrate the impact of SimO loss on the embedding space.
  arXiv  Detail & Related papers  (2024-10-07T17:41:10Z)
• Deep Clustering Using the Soft Silhouette Score: Towards Compact and Well-Separated Clusters [0.0]
  We propose soft silhoutte, a probabilistic formulation of the silhouette coefficient. We introduce an autoencoder-based deep learning architecture that is suitable for optimizing the soft silhouette objective function. The proposed deep clustering method has been tested and compared with several well-studied deep clustering methods on various benchmark datasets.
  arXiv  Detail & Related papers  (2024-02-01T14:02:06Z)
• Relaxed Contrastive Learning for Federated Learning [48.96253206661268]
  We propose a novel contrastive learning framework to address the challenges of data heterogeneity in federated learning. Our framework outperforms all existing federated learning approaches by huge margins on the standard benchmarks.
  arXiv  Detail & Related papers  (2024-01-10T04:55:24Z)
• Joint Training of Deep Ensembles Fails Due to Learner Collusion [61.557412796012535]
  Ensembles of machine learning models have been well established as a powerful method of improving performance over a single model. Traditionally, ensembling algorithms train their base learners independently or sequentially with the goal of optimizing their joint performance. We show that directly minimizing the loss of the ensemble appears to rarely be applied in practice.
  arXiv  Detail & Related papers  (2023-01-26T18:58:07Z)
• Deep Negative Correlation Classification [82.45045814842595]
  Existing deep ensemble methods naively train many different models and then aggregate their predictions. We propose deep negative correlation classification (DNCC) DNCC yields a deep classification ensemble where the individual estimator is both accurate and negatively correlated.
  arXiv  Detail & Related papers  (2022-12-14T07:35:20Z)
• Overlapping oriented imbalanced ensemble learning method based on projective clustering and stagewise hybrid sampling [22.32930261633615]
  This paper proposes an ensemble learning algorithm based on dual clustering and stage-wise hybrid sampling (DCSHS) The major advantage of our algorithm is that it can exploit the intersectionality of the CCS to realize the soft elimination of overlapping majority samples.
  arXiv  Detail & Related papers  (2022-11-30T01:49:06Z)
• 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)
• Cluster Analysis with Deep Embeddings and Contrastive Learning [0.0]
  This work proposes a novel framework for performing image clustering from deep embeddings. Our approach jointly learns representations and predicts cluster centers in an end-to-end manner. Our framework performs on par with widely accepted clustering methods and outperforms the state-of-the-art contrastive learning method on the CIFAR-10 dataset.
  arXiv  Detail & Related papers  (2021-09-26T22:18:15Z)
• Semi-supervised Contrastive Learning with Similarity Co-calibration [72.38187308270135]
  We propose a novel training strategy, termed as Semi-supervised Contrastive Learning (SsCL) SsCL combines the well-known contrastive loss in self-supervised learning with the cross entropy loss in semi-supervised learning. We show that SsCL produces more discriminative representation and is beneficial to few shot learning.
  arXiv  Detail & Related papers  (2021-05-16T09:13:56Z)
• Generalized Zero-Shot Learning Via Over-Complete Distribution [79.5140590952889]
  We propose to generate an Over-Complete Distribution (OCD) using Conditional Variational Autoencoder (CVAE) of both seen and unseen classes. The effectiveness of the framework is evaluated using both Zero-Shot Learning and Generalized Zero-Shot Learning protocols.
  arXiv  Detail & Related papers  (2020-04-01T19:05:28Z)

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.