mlsanityData to 14 Oct 2026

EDN: A Novel Edge-Dependent Noise Model for Graph Data

arXiv 2506.11368 ↗First posted 13 Jun 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

An important structural feature of a graph is its set of edges, as it captures the relationships among the nodes (the graph's topology). Existing node label noise models like Symmetric Label Noise (SLN) and Class Conditional Noise (CCN) disregard this important node relationship in graph data; and the Edge-Dependent Noise (EDN) model addresses this limitation. EDN posits that in real-world scenarios, label noise may be influenced by the connections between nodes. We explore three variants of EDN. A crucial notion that relates nodes and edges in a graph is the degree of a node; we show that in all three variants, the probability of a node's label corruption is dependent on its degree. Additionally, we compare the dependence of these probabilities on node degree across different variants. We performed experiments on popular graph datasets using 5 different GNN architectures and 8 noise robust algorithms for graph data. The results demonstrate that 2 variants of EDN lead to greater performance degradation in both Graph Neural Networks (GNNs) and existing noise-robust algorithms, as compared to traditional node label noise models. We statistically verify this by posing a suitable hypothesis-testing problem. This emphasizes the importance of incorporating EDN when evaluating noise robust algorithms for graphs, to enhance the reliability of graph-based learning in noisy environments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 28 references that are in the map. First posted on arXiv 13 Jun 2025.

Builds on

19 of 28 references.

References · 19

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  6. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  7. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  8. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
  9. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 506
  10. 2021NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphscited by 73
  11. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
  12. 2019A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learningcited by 31
7 more
  1. 2019Learning Graph Neural Networks with Noisy Labelscited by 30
  2. 2022Robust Training of Graph Neural Networks via Noise Governancecited by 29
  3. 2023Learning on Graphs under Label Noisecited by 22
  4. 2021Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactionscited by 21
  5. 2024NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label Noisecited by 17
  6. 2024ADEdgeDrop: Adversarial Edge Dropping for Robust Graph Neural Networkscited by 7
  7. 2025DeGLIF for Label Noise Robust Node Classification using GNNscited by 1

Built on by

Not cited yet.