← Back to all news
arXiv Machine Learning By Pintu Kumar, Nandyala Hemachandra

DeGLIF for Label Noise Robust Node Classification using GNNs

Read the original on arXiv Machine Learning →

The paper introduces DeGLIF, a denoising method for graph data that leverages a leave‑one‑out influence function to make node‑level predictions robust to label noise. DeGLIF uses a small clean subset and a theoretically motivated relabelling function to identify and correct noisy nodes without requiring knowledge of the noise model or level. Two variants of DeGLIF are proposed, one of which is proven to increase risk for detected noisy points, and experiments demonstrate that DeGLIF outperforms baseline algorithms on several datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 21

Particle Competition and Cooperation for Robust Graph Convolutional Network Learning Under Label Noise

Particle Competition and Cooperation for Robust Graph Convolutional Network Learning Under Label Noise proposes PCC+GCN, a hybrid framework that refines labels using Particle Competition and Cooperation before training a GCN. PCC identifies suspicious nodes via particle domination dynamics and decides whether to keep, remove, or reassign their labels, optionally augmenting the graph with k‑nearest‑neighbor edges. Evaluated on ten NoisyGL datasets under various noise types, PCC+GCN achieved the highest average accuracy and rank, outperforming baseline GCN by 1.67 percentage points and proving computationally efficient, especially under instance‑dependent noise.

By Fabricio Breve
benchmarks
More like this →
arXiv AI
Jun 19

Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement

arXiv:2606. 20283v1 Announce Type: cross Abstract: Graph neural networks (GNNs) excel at aggregating neighbor information for classification, yet their performance is hindered by graph structural entanglement, where spurious correlations from semantically irrelevant neighbors contaminate node embeddings.

By Jiaqing Chen, Zidu Yin, Yichao Cai, Yuhang Liu, Zhen Zhang, Dong Gong, Javen Qinfeng Shi
rag
More like this →