mlsanityData to 7 Oct 2026

Neural Gaussian Similarity Modeling for Differential Graph Structure Learning

arXiv 2312.09498 ↗First posted 15 Dec 2023cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph Structure Learning (GSL) has demonstrated considerable potential in the analysis of graph-unknown non-Euclidean data across a wide range of domains. However, constructing an end-to-end graph structure learning model poses a challenge due to the impediment of gradient flow caused by the nearest neighbor sampling strategy. In this paper, we construct a differential graph structure learning model by replacing the non-differentiable nearest neighbor sampling with a differentiable sampling using the reparameterization trick. Under this framework, we argue that the act of sampling mboxnearest neighbors may not invariably be essential, particularly in instances where node features exhibit a significant degree of similarity. To alleviate this issue, the bell-shaped Gaussian Similarity (GauSim) modeling is proposed to sample non-nearest neighbors. To adaptively model the similarity, we further propose Neural Gaussian Similarity (NeuralGauSim) with learnable parameters featuring flexible sampling behaviors. In addition, we develop a scalable method by transferring the large-scale graph to the transition graph to significantly reduce the complexity. Experimental results demonstrate the effectiveness of the proposed methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 27 references that are in the map. First posted on arXiv 15 Dec 2023.

Builds on

19 of 27 references.

References · 19

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  4. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  5. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  6. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  7. 2019Diffusion Improves Graph Learningcited by 414
  8. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  9. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 309
  10. 2019Learning Discrete Structures for Graph Neural Networkscited by 228
  11. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 207
  12. 2020Data Augmentation for Graph Neural Networkscited by 200
7 more
  1. 2022Vision GNN: An Image is Worth Graph of Nodescited by 185
  2. 2021A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directionscited by 144
  3. 2020AM-GCN: Adaptive Multi-channel Graph Convolutional Networkscited by 121
  4. 2021SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networkscited by 108
  5. 2021Graph Structure Learning with Variational Information Bottleneckcited by 81
  6. 2019Graph-Revised Convolutional Networkcited by 58
  7. 2021GNN-LM: Language Modeling based on Global Contexts via GNNcited by 27

Built on by

Not cited yet.