HPM-KD: Hierarchical Progressive Multi-Teacher Framework for Knowledge Distillation and Efficient Model Compression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Haase, Gustavo Coelho, da Silva, Paulo Henrique Dourado
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917137398890496
author Haase, Gustavo Coelho
da Silva, Paulo Henrique Dourado
author_facet Haase, Gustavo Coelho
da Silva, Paulo Henrique Dourado
contents Knowledge Distillation (KD) has emerged as a promising technique for model compression but faces critical limitations: (1) sensitivity to hyperparameters requiring extensive manual tuning, (2) capacity gap when distilling from very large teachers to small students, (3) suboptimal coordination in multi-teacher scenarios, and (4) inefficient use of computational resources. We present \textbf{HPM-KD}, a framework that integrates six synergistic components: (i) Adaptive Configuration Manager via meta-learning that eliminates manual hyperparameter tuning, (ii) Progressive Distillation Chain with automatically determined intermediate models, (iii) Attention-Weighted Multi-Teacher Ensemble that learns dynamic per-sample weights, (iv) Meta-Learned Temperature Scheduler that adapts temperature throughout training, (v) Parallel Processing Pipeline with intelligent load balancing, and (vi) Shared Optimization Memory for cross-experiment reuse. Experiments on CIFAR-10, CIFAR-100, and tabular datasets demonstrate that HPM-KD: achieves 10x-15x compression while maintaining 85% accuracy retention, eliminates the need for manual tuning, and reduces training time by 30-40% via parallelization. Ablation studies confirm independent contribution of each component (0.10-0.98 pp). HPM-KD is available as part of the open-source DeepBridge library.
format Preprint
id arxiv_https___arxiv_org_abs_2512_09886
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HPM-KD: Hierarchical Progressive Multi-Teacher Framework for Knowledge Distillation and Efficient Model Compression
Haase, Gustavo Coelho
da Silva, Paulo Henrique Dourado
Machine Learning
Applications
Knowledge Distillation (KD) has emerged as a promising technique for model compression but faces critical limitations: (1) sensitivity to hyperparameters requiring extensive manual tuning, (2) capacity gap when distilling from very large teachers to small students, (3) suboptimal coordination in multi-teacher scenarios, and (4) inefficient use of computational resources. We present \textbf{HPM-KD}, a framework that integrates six synergistic components: (i) Adaptive Configuration Manager via meta-learning that eliminates manual hyperparameter tuning, (ii) Progressive Distillation Chain with automatically determined intermediate models, (iii) Attention-Weighted Multi-Teacher Ensemble that learns dynamic per-sample weights, (iv) Meta-Learned Temperature Scheduler that adapts temperature throughout training, (v) Parallel Processing Pipeline with intelligent load balancing, and (vi) Shared Optimization Memory for cross-experiment reuse. Experiments on CIFAR-10, CIFAR-100, and tabular datasets demonstrate that HPM-KD: achieves 10x-15x compression while maintaining 85% accuracy retention, eliminates the need for manual tuning, and reduces training time by 30-40% via parallelization. Ablation studies confirm independent contribution of each component (0.10-0.98 pp). HPM-KD is available as part of the open-source DeepBridge library.
title HPM-KD: Hierarchical Progressive Multi-Teacher Framework for Knowledge Distillation and Efficient Model Compression
topic Machine Learning
Applications
url https://arxiv.org/abs/2512.09886