Distilling Lightweight Domain Experts from Large ML Models by Identifying Relevant Subspaces

2026-01-09

arXiv.org

AI Summary

This work addresses the challenge of efficiently transferring knowledge from a teacher model to a student model in resource-constrained settings, particularly when the focus is on specific subtasks—such as minority classes and their associated concepts. To this end, the authors propose SubDistill, an algorithm that explicitly identifies and distills task-relevant subspace features at each layer of the network, enabling layer-wise, subtask-oriented knowledge transfer. By doing so, SubDistill enhances numerical stability and improves the fidelity of the student model to the teacher’s decision structure. Experimental results on multiple subtasks of CIFAR-100 and ImageNet demonstrate that SubDistill outperforms existing layer-wise distillation methods, with the student model more accurately replicating the teacher’s decision logic.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Knowledge distillation involves transferring the predictive capabilities of large, high-performing AI models (teachers) to smaller models (students) that can operate in environments with limited computing power. In this paper, we address the scenario in which only a few classes and their associated intermediate concepts are relevant to distill. This scenario is common in practice, yet few existing distillation methods explicitly focus on the relevant subtask. To address this gap, we introduce'SubDistill', a new distillation algorithm with improved numerical properties that only distills the relevant components of the teacher model at each layer. Experiments on CIFAR-100 and ImageNet with Convolutional and Transformer models demonstrate that SubDistill outperforms existing layer-wise distillation techniques on a representative set of subtasks. Our benchmark evaluations are complemented by Explainable AI analyses showing that our distilled student models more closely match the decision structure of the original teacher model.

Problem

• knowledge distillation
• domain experts
• subtask-specific distillation
• lightweight models
• relevant subspaces

Innovation

• Subspace Distillation
• Task-Specific Knowledge Distillation
• Lightweight Student Models
• Explainable AI
• Layer-wise Distillation