PaSta introduces a Partial label-based Self‑training framework for noisy node classification on graphs. The method trains multiple annotators to generate high‑quality partial labels, then uses a partial‑label classification model with two loss functions to learn both labels and representations. A closed‑loop self‑training strategy further refines annotators, yielding an average 1.1% improvement over state‑of‑the‑art methods across five datasets.
By Yujing Liu, Yixin Liu, Yu Zheng, Yue Tan, Alan Wee-Chung Liew, Shirui Pan
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
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
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
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
arXiv:2606. 08718v1 Announce Type: cross Abstract: While Deep Active Learning (DAL) effectively reduces human annotation costs, its efficacy is constrained by human annotation errors.
By Md Abdullah Al Forhad, Weishi Shi
Federated Learning (FL) enables distributed clients to collaboratively train models without sharing raw data, making it promising for leveraging massive devices in communication networks. In distillat...
arXiv:2609.14451v1 Announce Type: cross
Abstract: Modern semi-supervised learning (SSL) couples pseudo-label generation and classifier training, using the classifier's own confidence to select the ps...
By Itai David, Daphna Weinshall
arXiv:2506. 10292v2 Announce Type: replace-cross Abstract: Training deep learning networks with minimal supervision has gained significant research attention due to its potential to reduce reliance on extensive labelled data.
By Ali Almutairi, Abdullah Alsuhaibani, Shoaib Jameel, Aditya Joshi, Gelareh Mohammadi, Imran Razzak
arXiv:2405. 03386v2 Announce Type: replace Abstract: Training with noisy class labels impairs neural networks' generalization performance.
By Marek Herde, Lukas L\"uhrs, Denis Huseljic, Bernhard Sick
arXiv:2606. 11699v1 Announce Type: new Abstract: The performance of machine learning and deep learning models largely depends on the quality of the training data.
By Ha-Linh Nguyen, Hong-Anh Nguyen, Minh-Duc La, Thu-Trang Nguyen, Son Nguyen, Hieu Dinh Vo