Conveyance: A Versatile Framework for Learning in Structured Class Spaces

• URL: http://arxiv.org/abs/2605.28420v2
• Date: Fri, 29 May 2026 10:37:33 GMT
• Title: Conveyance: A Versatile Framework for Learning in Structured Class Spaces
• Abstract summary: Loss functions like cross-entropy remain mostly structure-agnostic in many real-world applications.<n>We propose a new classification approach and associated loss function tailored to structured class spaces.
• Score: 5.204620543649613
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While machine learning (ML) architectures have evolved rapidly to account for complex data, loss functions like cross-entropy remain mostly structure-agnostic in many real-world applications. However, the "class-symmetric" nature of these standard losses fundamentally limits the ability of ML models to exploit structural relationships between classes, particularly when facing structured noise. We propose Conveyance, a new classification approach and associated loss function tailored to structured class spaces. It allows users to encode graph-like relations between classes without having to define complex joint distributions or manually tune utility matrices. Technically, our loss function operates by maximizing two separate margins over distinct class partitions, while preserving formal properties such as monotonicity and partial convexity. We demonstrate the versatility and effectiveness of our method by applying it to hierarchical classification, ordinal regression, and multiple instance learning. Across these tasks, Conveyance either matches or exceeds the performance of specialized baselines, thereby offering a unified solution for structured class spaces.

Related papers

• A Leakage-Free Stacked Ensemble Method for Multiclass Classification [1.1090533263502935]
  We propose a Leakage-Free Stacked ensemble framework that integrates functional learning and rule-based learning for robust multiclass classification.<n>The framework constructs unbiased meta-features by employing a strict out-of-fold stacking strategy to ensure complete isolation between training and validation data.<n> Experimental evaluations on multi-class datasets demonstrate that LFS-FRAME improves performance metrics.
  arXiv  Detail & Related papers  (2026-07-24T08:26:40Z)
• Online Continual Learning with Dynamic Label Hierarchies [72.33335166136045]
  We introduce a new problem setting, DHOCL, where severity evolve across granularities and each sample provides supervision at a single hierarchical level.<n>In this setting, we find two fundamental issues: (i) partial supervision under mixed granularities provides only point-wise signals over an evolving path-wise hierarchy, which constrains plasticity and undermines cross-level semantic consistency.<n>We propose HALO, which adaptively combines complementary classification heads, regularized by organized learnable hierarchical prototypes, enabling rapid adaptation, hierarchical consistency, and structured knowledge consolidation as the taxonomy evolves.
  arXiv  Detail & Related papers  (2026-05-12T08:20:23Z)
• Continual Hyperbolic Learning of Instances and Classes [41.32412210317651]
  We introduce the task of continual learning of instances and classes, at the same time.<n>This task challenges models to adapt to multiple levels of granularity over time.<n>In this paper, we identify that classes and instances naturally form a hierarchical structure.
  arXiv  Detail & Related papers  (2025-06-12T13:59:57Z)
• CAARMA: Class Augmentation with Adversarial Mixup Regularization [59.938216853878636]
  Speaker verification is a typical zero-shot learning task.<n>We introduce CAARMA, a class augmentation framework.<n>Our framework demonstrates a significant improvement of 8% over all baseline models.
  arXiv  Detail & Related papers  (2025-03-20T21:41:16Z)
• Harnessing Superclasses for Learning from Hierarchical Databases [1.835004446596942]
  In many large-scale classification problems, classes are organized in a known hierarchy, typically represented as a tree. We introduce a loss for this type of supervised hierarchical classification. Our approach does not entail any significant additional computational cost compared with the loss of cross-entropy.
  arXiv  Detail & Related papers  (2024-11-25T14:39:52Z)
• Domain-Agnostic Neural Architecture for Class Incremental Continual Learning in Document Processing Platform [3.630365560970225]
  Recent methods with learning gradient have been shown to struggle in such setups or have limitations like memory buffers. We present a fully differentiable architecture based on the Mixture of Experts model, that enables the training of high-performance classifiers when examples from each class are presented separately. We conducted exhaustive experiments that proved its applicability in various domains and ability to learn online in production environments.
  arXiv  Detail & Related papers  (2023-07-11T16:01:44Z)
• Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework [75.79736930414715]
  We present a hierarchical multi-label representation learning framework that can leverage all available labels and preserve the hierarchical relationship between classes. We introduce novel hierarchy preserving losses, which jointly apply a hierarchical penalty to the contrastive loss, and enforce the hierarchy constraint.
  arXiv  Detail & Related papers  (2022-04-27T21:41:44Z)
• Few-Shot Object Detection via Association and DIscrimination [83.8472428718097]
  Few-shot object detection via Association and DIscrimination builds up a discriminative feature space for each novel class with two integral steps. Experiments on Pascal VOC and MS-COCO datasets demonstrate FADI achieves new SOTA performance, significantly improving the baseline in any shot/split by +18.7.
  arXiv  Detail & Related papers  (2021-11-23T05:04:06Z)
• Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation [66.85202434812942]
  We reformulate few-shot segmentation as a semantic reconstruction problem. We convert base class features into a series of basis vectors which span a class-level semantic space for novel class reconstruction. Our proposed approach, referred to as anti-aliasing semantic reconstruction (ASR), provides a systematic yet interpretable solution for few-shot learning problems.
  arXiv  Detail & Related papers  (2021-06-01T02:17:36Z)
• Hierarchical Proxy-based Loss for Deep Metric Learning [32.10423536428467]
  Proxy-based metric learning losses are superior to pair-based losses due to their fast convergence and low training complexity. We present a framework that leverages this implicit hierarchy by imposing a hierarchical structure on the proxies. Results demonstrate that our hierarchical proxy-based loss framework improves the performance of existing proxy-based losses.
  arXiv  Detail & Related papers  (2021-03-25T00:38:33Z)
• Leveraging Class Hierarchies with Metric-Guided Prototype Learning [5.070542698701158]
  In many classification tasks, the set of target classes can be organized into a hierarchy. This structure induces a semantic distance between classes, and can be summarised under the form of a cost matrix. We propose to model the hierarchical class structure by integrating this metric in the supervision of a prototypical network.
  arXiv  Detail & Related papers  (2020-07-06T20:22:08Z)
• MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures [61.73533544385352]
  We propose a transferable perturbation, MetaPerturb, which is meta-learned to improve generalization performance on unseen data. As MetaPerturb is a set-function trained over diverse distributions across layers and tasks, it can generalize heterogeneous tasks and architectures.
  arXiv  Detail & Related papers  (2020-06-13T02:54:59Z)

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.