LGAIDec 15, 2023

Neural Gaussian Similarity Modeling for Differential Graph Structure Learning

arXiv:2312.09498v11 citationsh-index: 27AAAI
Originality Incremental advance
AI Analysis

This work addresses a gradient flow problem in graph structure learning for domains with graph-unknown non-Euclidean data, representing an incremental improvement.

The paper tackles the challenge of gradient flow obstruction in end-to-end graph structure learning by introducing a differentiable sampling method using the reparameterization trick, and proposes Neural Gaussian Similarity to sample non-nearest neighbors, achieving effective results in experiments.

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 \mbox{nearest} 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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes