Hugging Face Trending Papers
PaSta: Noisy Node Classification with Partial Label Learning
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Machine Learning
Aug 27
PaSta: Noisy Node Classification with Partial Label Learning
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.
arXiv Machine Learning
6d ago
Label Ensemble Perspective for Reduced-Complexity Graph Node Classification under Label Noise
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.
Hugging Face Trending Papers
Aug 7
Recent advances in weakly supervised learning: New supervision paradigms, assumption relaxations, and practical solutions
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.
arXiv AI
Aug 25
FedCC: Towards Addressing Label Distribution Skews in Distillation-Based Federated Learning
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 Machine Learning
Aug 10
Recent advances in weakly supervised learning: New supervision paradigms, assumption relaxations, and practical solutions
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.
arXiv AI
Sep 18
Pre-train to Gain: Robust Learning Without Clean Labels
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.