Independence Promoted Graph Disentangled Networks
This work addresses the challenge of disentangling latent factors in graph data, which is crucial for improving interpretability and performance in network applications, though it appears incremental as it builds on existing graph convolutional frameworks.
The paper tackles the problem of learning disentangled node representations in graph convolutional networks by promoting independence among latent factors, and demonstrates that their method outperforms state-of-the-art approaches in tasks like semi-supervised graph classification, graph clustering, and graph visualization.
We address the problem of disentangled representation learning with independent latent factors in graph convolutional networks (GCNs). The current methods usually learn node representation by describing its neighborhood as a perceptual whole in a holistic manner while ignoring the entanglement of the latent factors. However, a real-world graph is formed by the complex interaction of many latent factors (e.g., the same hobby, education or work in social network). While little effort has been made toward exploring the disentangled representation in GCNs. In this paper, we propose a novel Independence Promoted Graph Disentangled Networks (IPGDN) to learn disentangled node representation while enhancing the independence among node representations. In particular, we firstly present disentangled representation learning by neighborhood routing mechanism, and then employ the Hilbert-Schmidt Independence Criterion (HSIC) to enforce independence between the latent representations, which is effectively integrated into a graph convolutional framework as a regularizer at the output layer. Experimental studies on real-world graphs validate our model and demonstrate that our algorithms outperform the state-of-the-arts by a wide margin in different network applications, including semi-supervised graph classification, graph clustering and graph visualization.