mlsanityData to 7 Oct 2026

Probability Passing for Graph Neural Networks: Graph Structure and Representations Joint Learning

arXiv 2407.10688 ↗First posted 15 Jul 2024cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have achieved notable success in the analysis of non-Euclidean data across a wide range of domains. However, their applicability is constrained by the dependence on the observed graph structure. To solve this problem, Latent Graph Inference (LGI) is proposed to infer a task-specific latent structure by computing similarity or edge probability of node features and then apply a GNN to produce predictions. Even so, existing approaches neglect the noise from node features, which affects generated graph structure and performance. In this work, we introduce a novel method called Probability Passing to refine the generated graph structure by aggregating edge probabilities of neighboring nodes based on observed graph. Furthermore, we continue to utilize the LGI framework, inputting the refined graph structure and node features into GNNs to obtain predictions. We name the proposed scheme as Probability Passing-based Graph Neural Network (PPGNN). Moreover, the anchor-based technique is employed to reduce complexity and improve efficiency. Experimental results demonstrate the effectiveness of the proposed method.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 35 references that are in the map. First posted on arXiv 15 Jul 2024.

Builds on

24 of 35 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  7. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  8. 2015Image-based Recommendations on Styles and Substitutescited by 702
  9. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
  10. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 471
  11. 2019Learning Discrete Structures for Graph Neural Networkscited by 228
  12. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 212
12 more
  1. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 207
  2. 2019Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacementcited by 205
  3. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  4. 2021SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networkscited by 108
  5. 2020Differentiable Graph Module (DGM) for Graph Convolutional Networkscited by 86
  6. 2022Multimodal learning with graphscited by 54
  7. 2019Modality to Modality Translation: An Adversarial Representation Learning and Graph Fusion Network for Multimodal Fusioncited by 45
  8. 2023Beyond Homophily: Reconstructing Structure for Graph-agnostic Clusteringcited by 29
  9. 2022Latent Graph Inference using Product Manifoldscited by 23
  10. 2019Deep Iterative and Adaptive Learning for Graph Neural Networkscited by 17
  11. 2019Scalable Global Alignment Graph Kernel Using Random Features: From Node Embedding to Graph Embeddingcited by 8
  12. 2022Self-organization Preserved Graph Structure Learning with Principle of Relevant Informationcited by 8

Built on by

Not cited yet.