Search Results for author:
Found 3 papers, 2 papers with code
EntropyStop: Unsupervised Deep Outlier Detection with Loss Entropy
Most deep UOD models are trained exclusively on clean datasets to learn the distribution of the normal data, which requires huge manual efforts to clean the real-world data if possible.
Unleashing the Potential of Unsupervised Deep Outlier Detection through Automated Training Stopping
To our knowledge, our approach is the first to enable reliable identification of the optimal training iteration during training without requiring any labels.
Unsupervised Graph Outlier Detection: Problem Revisit, New Insight, and Superior Method
In addition, we observe that existing algorithms have a performance drop with the mitigated data leakage issue.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
