mlsanityData to 14 Oct 2026

Optimal Propagation for Graph Neural Networks

arXiv 2205.02998 ↗First posted 6 May 2022cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have achieved tremendous success in a variety of real-world applications by relying on the fixed graph data as input. However, the initial input graph might not be optimal in terms of specific downstream tasks, because of information scarcity, noise, adversarial attacks, or discrepancies between the distribution in graph topology, features, and groundtruth labels. In this paper, we propose a bi-level optimization approach for learning the optimal graph structure via directly learning the Personalized PageRank propagation matrix as well as the downstream semi-supervised node classification simultaneously. We also explore a low-rank approximation model for further reducing the time complexity. Empirical evaluations show the superior efficacy and robustness of the proposed model over all baseline methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 42 references that are in the map. First posted on arXiv 6 May 2022.

Builds on

23 of 42 references.

References · 23

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  4. 2019Simplifying Graph Convolutional Networkscited by 1,477
  5. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
  6. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  7. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
  8. 2019Diffusion Improves Graph Learningcited by 414
  9. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  10. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 335
  11. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
  12. 2019Learning Discrete Structures for Graph Neural Networkscited by 231
11 more
  1. 2020Scaling Graph Neural Networks with Approximate PageRankcited by 174
  2. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 133
  3. 2020Learning to Drop: Robust Graph Neural Network via Topological Denoisingcited by 127
  4. 2020Scalable Graph Neural Networks via Bidirectional Propagationcited by 87
  5. 2018GAMENet: Graph Augmented MEmory Networks for Recommending Medication Combinationcited by 83
  6. 2021Approximate Graph Propagationcited by 21
  7. 2021Graph Sanitation with Application to Node Classificationcited by 20
  8. 2019Efficient Estimation of Heat Kernel PageRank for Local Clusteringcited by 9
  9. 2021Topological Regularization for Graph Neural Networks Augmentationcited by 8
  10. 2013Personalized PageRank to a Target Nodecited by 6
  11. 2021Node Embedding using Mutual Information and Self-Supervision based Bi-level Aggregationcited by 5

Built on by

Not cited yet.