Summary of Self-degraded Contrastive Domain Adaptation For Industrial Fault Diagnosis with Bi-imbalanced Data, by Gecheng Chen et al.
Self-degraded contrastive domain adaptation for industrial fault diagnosis with bi-imbalanced data
by Gecheng Chen, Zeyu Yang, Chengwen Luo, Jianqiang Li
First submitted to arxiv on: 31 May 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a self-degraded contrastive domain adaptation framework, Sd-CDA, to diagnose industrial faults in the presence of distribution discrepancy and bi-imbalance. The approach first pre-trains a feature extractor using imbalance-aware contrastive learning based on model pruning, followed by supervised contrastive domain adversarial learning (SupCon-DA) to push samples away from the domain boundary. Additionally, the authors introduce pruned contrastive domain adversarial learning (PSupCon-DA), which automatically re-weights attention to minorities for improved performance under bi-imbalanced data. Experimental results demonstrate the superiority of Sd-CDA over existing methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about finding a way to diagnose problems with machines and factories, even when the data used to train the system is different from the real-world situations it will face. The authors are trying to solve this problem by developing a new approach that can learn from both balanced and imbalanced data sets. They tested their method on two experiments and found that it outperformed existing methods. |
Keywords
» Artificial intelligence » Attention » Domain adaptation » Pruning » Supervised
