The paper introduces LENS, a lightweight algorithm that detects noisy labels in graph data by measuring how removing a node reduces neighborhood entropy. It shows that label noise increases entropy and blurs class boundaries, and proposes a relabeling step to preserve useful features. Experiments demonstrate that LENS outperforms existing noise‑robust methods in accuracy while being an order of magnitude faster.
By Pintu Kumar, Nandyala Hemachandra
arXiv:2601. 17469v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have shown remarkable capabilities in learning from graph-structured data with various applications such as social analysis and bioinformatics.
By Wei Ju, Wei Zhang, Siyu Yi, Zhengyang Mao, Yifan Wang, Jingyang Yuan, Zhiping Xiao, Ziyue Qiao, Ming Zhang
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
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.
By Pintu Kumar, Nandyala Hemachandra
The paper introduces SEMGNN, an end‑to‑end self‑explainable multi‑label graph neural network that simultaneously classifies nodes and identifies edges contributing to each predicted label. Unlike post‑hoc explainers, SEMGNN jointly learns a predictor and a sparse edge‑mask explainer, leveraging label‑label correlations to improve classification and generate distinct, coherent explanations for each label. Experiments on synthetic and real‑world networks in social, entertainment, and life‑science domains demonstrate competitive predictive performance and more faithful, compact label‑conditioned explanations.
By Yingqi Feng, Yufei Tang, Min Shi, Xingquan Zhu
GraphIFE addresses the class imbalance problem in graph-structured data by tackling a quality inconsistency issue in synthesized nodes. The framework uses graph invariant learning to strengthen embedding space representations and identify invariant features, leading to improved performance on minority classes. Experiments show that GraphIFE consistently outperforms various baselines across multiple datasets.
By Fanlong Zeng, Wensheng Gan, Kangjie Chen, Philip S. Yu