LGJan 12, 2024

Deep Manifold Graph Auto-Encoder for Attributed Graph Embedding

arXiv:2401.06727v15 citationsh-index: 44ICASSP
Originality Highly original
AI Analysis

This work addresses the crowding problem in graph embeddings for real-world data, offering a novel approach that enhances representation quality for tasks like node classification or link prediction.

The paper tackles the problem of attributed graph embedding by proposing a Deep Manifold Graph Auto-Encoder that simultaneously considers data distribution and topological structure to improve stability and quality, achieving significant performance gains over state-of-the-art baselines on downstream tasks across popular datasets.

Representing graph data in a low-dimensional space for subsequent tasks is the purpose of attributed graph embedding. Most existing neural network approaches learn latent representations by minimizing reconstruction errors. Rare work considers the data distribution and the topological structure of latent codes simultaneously, which often results in inferior embeddings in real-world graph data. This paper proposes a novel Deep Manifold (Variational) Graph Auto-Encoder (DMVGAE/DMGAE) method for attributed graph data to improve the stability and quality of learned representations to tackle the crowding problem. The node-to-node geodesic similarity is preserved between the original and latent space under a pre-defined distribution. The proposed method surpasses state-of-the-art baseline algorithms by a significant margin on different downstream tasks across popular datasets, which validates our solutions. We promise to release the code after acceptance.

Foundations

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

Your Notes