paper-with-me

홈 › Papers

Hierarchical Class-Based Curriculum Loss

2020-06-05 · Palash Goyal, Shalini Ghosh

Classification algorithms in machine learning often assume a flat label space. However, most real world data have dependencies between the labels, which can often be captured by using a hierarchy. Utilizing this relation can help develop a model capable of satisfying the dependencies and improving model accuracy and interpretability. Further, as different levels in the hierarchy correspond to different granularities, penalizing each label equally can be detrimental to model learning. In this paper, we propose a loss function, hierarchical curriculum loss, with two properties: (i) satisfy hierarchical constraints present in the label space, and (ii) provide non-uniform weights to labels based on their levels in the hierarchy, learned implicitly by the training paradigm. We theoretically show that the proposed loss function is a tighter bound of 0-1 loss compared to any other loss satisfying the hierarchical constraints. We test our loss function on real world image data sets, and show that it significantly substantially outperforms multiple baselines.

📄 PDF Abstract BibTeX arXiv:2006.03629

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Target Curricula via Selection of Minimum Feature Sets: a Case Study in Boolean Networks

2017-06-15 · Shannon Fenn, Pablo Moscato

We consider the effect of introducing a curriculum of targets when training Boolean models on supervised Multi Label Classification (MLC) problems. In particular, we consider how to order targets in the absence of prior …

Multi-Label ClassificationMUlTI-LABEL-ClASSIFICATION

Hierarchical Semantic Learning for Multi-Class Aorta Segmentation

2025-11-18 · Pengcheng Shi arxiv

The aorta, the body's largest artery, is prone to pathologies such as dissection, aneurysm, and atherosclerosis, which often require timely intervention. Minimally invasive repairs involving branch vessels necessitate de…

Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents

2025-09-26 · Heyang Gao, Zexu Sun, Erxue Min, Hengyi Cai 외 arxiv

Large Language Models (LLMs) as autonomous agents are increasingly tasked with solving complex, long-horizon problems. Aligning these agents via preference-based offline methods like Direct Preference Optimization (DPO) …

Adaptive Curriculum Learning

2021-01-01 · ICCV 2021 10 · Yajing Kong, Liu Liu, Jun Wang, DaCheng Tao

Inspired by the human learning principle that learning easier concepts first and then gradually paying more attention to harder ones, curriculum learning uses the non-uniform sampling of mini-batches according to the…

Binary Classification

Dynamic Curriculum Learning for Imbalanced Data Classification

2019-01-21 · ICCV 2019 10 · Yiru Wang, Weihao Gan, Jie Yang, Wei Wu 외

Human attribute analysis is a challenging task in the field of computer vision, since the data is largely imbalance-distributed. Common techniques such as re-sampling and cost-sensitive learning require prior-knowledge t…

AttributeClassificationGeneral ClassificationMetric Learning