Noisy node classification problem is a fundamental yet challenging task for real-world graph-related web services, where node labels are often corrupted or unreliable due to weak supervision or automa...
The paper introduces LEGNN, a lower‑complexity Graph Neural Network designed to handle label noise in node classification. LEGNN reframes the problem as a label ensemble task, using random neighbor masks to gather high‑probability label sets and a partial‑label learning strategy to aggregate them, while also collecting low‑probability labels to mitigate noise. Experiments on six datasets show that LEGNN achieves strong classification performance, computational efficiency, and scalability to graphs with over a hundred thousand nodes and one million edges.
By Rui Zhao, Bin Shi, Zhiming Liang, Jianfei Ruan, Kai Sun, Bo Dong, Lu Lin
arXiv:2608. 06896v1 Announce Type: new Abstract: Deep learning has achieved great success in recent years thanks to the availability of high-quality, well-annotated training data.
By Wei Wang, Gang Niu, Masashi Sugiyama
Deep learning has achieved great success in recent years thanks to the availability of high-quality, well-annotated training data. However, this requirement is often not met in real-world applications.
FedCC is a new algorithm for distillation-based federated learning that tackles label distribution skew by allowing clients to mark ambiguous samples as 'unknown' instead of forcing a potentially wrong classification. By adding this extra class and calibrating pseudo-labels on a public dataset, FedCC balances confidence across majority and minority classes. Experiments show that FedCC outperforms existing methods, achieving 67.3% accuracy even when each client has data from only one of ten classes, whereas baselines drop to near-random performance.
By Wenxuan Ye, Onur Ayan, Xueli An, Georg Carle
The paper proposes a method that first pre‑trains a feature extractor on the target dataset using in‑domain self‑supervised learning (SSL) without labels, then performs standard supervised training on the same noisy dataset. This two‑stage approach eliminates the need for a clean label subset and consistently improves classification accuracy and label‑error detection across synthetic and real‑world noise, especially as noise rates increase. Experiments show that the method matches or surpasses ImageNet and DinoV2 pre‑training, particularly under high noise conditions.
By David Szczecina, Nicholas Pellegrino, Paul Fieguth