# Hierarchy-Consistent Learning and Adaptive Loss Balancing for Hierarchical Multi-Label Classification

arXiv: https://arxiv.org/abs/2508.13452 · HTML: https://mlsanity.com/paper/2508.13452/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Builds on (most cited first, 19 of 19)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [FedProto: Federated Prototype Learning across Heterogeneous Clients](https://mlsanity.com/paper/2105.00243/) (2021)
- [Multi-Task Deep Neural Networks for Natural Language Understanding](https://mlsanity.com/paper/1901.11504/) (2019)
- [Multi-Task Learning as a Bargaining Game](https://mlsanity.com/paper/2202.01017/) (2022)
- [Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyond](https://mlsanity.com/paper/2401.01219/) (2024)
- [Prototypical Verbalizer for Prompt-based Few-shot Tuning](https://mlsanity.com/paper/2203.09770/) (2022)
- [Online Prototype Learning for Online Continual Learning](https://mlsanity.com/paper/2308.00301/) (2023)
- [Multi-Label Classification Neural Networks with Hard Logical Constraints](https://mlsanity.com/paper/2103.13427/) (2021)
- [Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning](https://mlsanity.com/paper/2303.14771/) (2023)
- [Hyperbolic Interaction Model For Hierarchical Multi-Label Classification](https://mlsanity.com/paper/1905.10802/) (2019)
- [Label Relation Graphs Enhanced Hierarchical Residual Network for Hierarchical Multi-Granularity Classification](https://mlsanity.com/paper/2201.03194/) (2022)
- [Adversarial Contrastive Learning via Asymmetric InfoNCE](https://mlsanity.com/paper/2207.08374/) (2022)
- [Error Detection and Constraint Recovery in Hierarchical Multi-Label Classification without Prior Knowledge](https://mlsanity.com/paper/2407.15192/) (2024)
- [PrototypeFormer: Learning to Explore Prototype Relationships for Few-shot Image Classification](https://mlsanity.com/paper/2310.03517/) (2023)
- [HSVLT: Hierarchical Scale-Aware Vision-Language Transformer for Multi-Label Image Classification](https://mlsanity.com/paper/2407.16244/) (2024)
- [Jointly Modeling Heterogeneous Student Behaviors and Interactions Among Multiple Prediction Tasks](https://mlsanity.com/paper/2103.13565/) (2021)

## Built on by (most cited first, 2 of 2)

- [Mitigating The Effect of Class Imbalance in Data with Hierarchical and Dependable Structure](https://mlsanity.com/paper/2607.11994/) (2026)
- [A Hierarchy-Aware Video-Language Model Evaluation and Hyperbolic Baseline for Surgery](https://mlsanity.com/paper/2609.27139/) (2026)

## Abstract (arXiv)

Hierarchical Multi-Label Classification (HMC) faces critical challenges in maintaining structural consistency and balancing loss weighting in Multi-Task Learning (MTL). In order to address these issues, we propose a classifier called HCAL based on MTL integrated with prototype contrastive learning and adaptive task-weighting mechanisms. The most significant advantage of our classifier is semantic consistency including both prototype with explicitly modeling label and feature aggregation from child classes to parent classes. The other important advantage is an adaptive loss-weighting mechanism that dynamically allocates optimization resources by monitoring task-specific convergence rates. It effectively resolves the "one-strong-many-weak" optimization bias inherent in traditional MTL approaches. To further enhance robustness, a prototype perturbation mechanism is formulated by injecting controlled noise into prototype to expand decision boundaries. Additionally, we formalize a quantitative metric called Hierarchical Violation Rate (HVR) as to evaluate hierarchical consistency and generalization. Extensive experiments across three datasets demonstrate both the higher classification accuracy and reduced hierarchical violation rate of the proposed classifier over baseline models.