Unsupervised Deep Manifold Attributed Graph Embedding
This work addresses limitations in graph embedding for applications like visualization and clustering, offering a novel approach to improve representation quality, though it is incremental in advancing existing methods.
The paper tackled the challenge of unsupervised attributed graph representation learning by proposing DMAGE, a framework that optimizes latent representations using geodesic similarity and Bergman divergence, achieving significant improvements over state-of-the-art methods on tasks like node clustering and link prediction across four datasets.
Unsupervised attributed graph representation learning is challenging since both structural and feature information are required to be represented in the latent space. Existing methods concentrate on learning latent representation via reconstruction tasks, but cannot directly optimize representation and are prone to oversmoothing, thus limiting the applications on downstream tasks. To alleviate these issues, we propose a novel graph embedding framework named Deep Manifold Attributed Graph Embedding (DMAGE). A node-to-node geodesic similarity is proposed to compute the inter-node similarity between the data space and the latent space and then use Bergman divergence as loss function to minimize the difference between them. We then design a new network structure with fewer aggregation to alleviate the oversmoothing problem and incorporate graph structure augmentation to improve the representation's stability. Our proposed DMAGE surpasses state-of-the-art methods by a significant margin on three downstream tasks: unsupervised visualization, node clustering, and link prediction across four popular datasets.