← Back to all news
arXiv Machine Learning By Yuanye Liu, Xiahai Zhuang

H$^2$EDL: Hyper Evidential Deep Learning for Hierarchical Classification

Read the original on arXiv Machine Learning →

The paper introduces H$^2$EDL, a Hyper Evidential Deep Learning framework that unifies flat evidential classification and hierarchical classification by leveraging the taxonomy itself as a hyperdomain. By assigning one local Dirichlet opinion per branching node, the model generates a linear‑size focal family that captures both fine‑grained class uncertainty and intermediate concept belief. Experiments on FGVC‑Aircraft and DERM12345 show that H$^2$EDL halves calibration error relative to cross‑entropy baselines, especially at deeper hierarchy levels and with larger training budgets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jul 30

The Advantage of Fine-Grained Training

arXiv:2509. 05130v2 Announce Type: replace Abstract: In classification problems, models are trained to predict a class label based on the input data features.

By Davide Pirovano, Federico Milanesio, Michele Caselle, Piero Fariselli, Matteo Osella
safety
More like this →
arXiv Machine Learning
Sep 10

Deep learning from the crowd Fundamentals of morphological galaxy classification

The study adapts a convolutional neural network to classify galaxy morphologies using crowd-sourced annotations from Galaxy Zoo 1. It evaluates how training strategies—such as training all layers versus only the last, incorporating hierarchical labels, varying data volume and annotator agreement, staged transfer learning, and ensembling—affect accuracy and efficiency. Results show that full-network training and high annotator agreement yield over 99% accuracy, while hierarchical approaches and staged learning help when data are limited.

By Luis Enrique Sucar, Carlos del Burgo, Jonathan Serrano-P\'erez
fine-tuning
More like this →
arXiv Machine Learning
Aug 27

Toward Machine Learning with the Unit as a Primitive: Learning from Unit-Linked Events

The paper proposes treating the ‘unit’—a persistent referent that multiple events may refer to—as an explicit primitive in machine learning tasks. It formalizes supervised learning as learning a pair of a tokenizer that generates a contextual unit token and a shared response law that uses this token, thereby distinguishing homogeneous from heterogeneous worlds. The work also introduces concepts such as unit abduction and trusted resolvers to handle cases where unit identity is unresolved.

By Heyang Gong
nlp
More like this →