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.
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...
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.
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.
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.
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.
arXiv:2606. 11695v1 Announce Type: cross Abstract: High-quality labeled data is essential for training reliable ML/DL models.
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:2405. 03386v2 Announce Type: replace Abstract: Training with noisy class labels impairs neural networks' generalization performance.
Large language models (LLMs) are increasingly used to annotate datasets for training smaller, task‑specialized models such as named entity recognition (NER). However, current fine‑tuning processes ignore the annotation noise introduced by LLMs, leading to degraded performance, and existing noise‑robust losses fail to handle the heterogeneous nature of NER noise (e.g., missing mentions vs. type errors). The authors propose error‑type‑aware loss reweighting, which applies separate reweighting rules for different erroneous token types, improving F1 scores by 0.8–2.0 percentage points on average and up to 4.6 points on Wikigold at 24.1% noise.
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.
JEPAMatch introduces a new semi‑supervised learning framework that replaces traditional output‑thresholding with explicit geometric shaping of latent representations. By combining the FlexMatch loss with a latent‑space regularization inspired by LeJEPA, the method encourages isotropic Gaussian structure in the embedding space, mitigating class imbalance and noisy pseudo‑labels. Experiments on CIFAR‑100, STL‑10, and Tiny‑ImageNet show consistent performance gains and faster convergence compared to existing FixMatch‑based baselines.