# Knowledge Distillation and Enhanced Subdomain Adaptation Using Graph Convolutional Network for Resource-Constrained Bearing Fault Diagnosis

arXiv: https://arxiv.org/abs/2501.07173 · HTML: https://mlsanity.com/paper/2501.07173/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Graph neural network distillation, one of 12 directions in Knowledge distillation.
- Builds on 9 of its 66 references that are in the map.
- First posted on arXiv 13 Jan 2025.

## Placed in

- Knowledge distillation / [Graph neural network distillation](https://mlsanity.com/distill/graph-neural-network-distillation/)

## Builds on (most cited first, 9 of 9)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Graph Neural Networks with convolutional ARMA filters](https://mlsanity.com/paper/1901.01343/) (2019)
- [Deep Subdomain Adaptation Network for Image Classification](https://mlsanity.com/paper/2106.09388/) (2021)
- [Applications of Unsupervised Deep Transfer Learning to Intelligent Fault Diagnosis: A Survey and Comparative Study](https://mlsanity.com/paper/1912.12528/) (2019)
- [Spatial Graph Convolutional Neural Network via Structured Subdomain Adaptation and Domain Adversarial Learning for Bearing Fault Diagnosis](https://mlsanity.com/paper/2112.06033/) (2021)
- [Combining inherent knowledge of vision-language models with unsupervised domain adaptation through strong-weak guidance](https://mlsanity.com/paper/2312.04066/) (2023)
- [A CNN-BiLSTM Model with Attention Mechanism for Earthquake Prediction](https://mlsanity.com/paper/2112.13444/) (2021)
- [Physics-Informed Deep Learning and Partial Transfer Learning for Bearing Fault Diagnosis in the Presence of Highly Missing Data](https://mlsanity.com/paper/2406.11023/) (2024)

## Abstract (arXiv)

Bearing fault diagnosis under varying working conditions faces challenges, including a lack of labeled data, distribution discrepancies, and resource constraints. To address these issues, we propose a progressive knowledge distillation framework that transfers knowledge from a complex teacher model, utilizing a Graph Convolutional Network (GCN) with Autoregressive moving average (ARMA) filters, to a compact and efficient student model. To mitigate distribution discrepancies and labeling uncertainty, we introduce Enhanced Local Maximum Mean Squared Discrepancy (ELMMSD), which leverages mean and variance statistics in the Reproducing Kernel Hilbert Space (RKHS) and incorporates a priori probability distributions between labels. This approach increases the distance between clustering centers, bridges subdomain gaps, and enhances subdomain alignment reliability. Experimental results on benchmark datasets (CWRU and JNU) demonstrate that the proposed method achieves superior diagnostic accuracy while significantly reducing computational costs. Comprehensive ablation studies validate the effectiveness of each component, highlighting the robustness and adaptability of the approach across diverse working conditions.