# Interpretable Deep Graph Generation with Node-Edge Co-Disentanglement

arXiv: https://arxiv.org/abs/2006.05385 · HTML: https://mlsanity.com/paper/2006.05385/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2020.

## Built on by (most cited first, 24 of 24)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Out-Of-Distribution Generalization on Graphs: A Survey](https://mlsanity.com/paper/2202.07987/) (2022)
- [A Survey on Deep Graph Generation: Methods and Applications](https://mlsanity.com/paper/2203.06714/) (2022)
- [Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment](https://mlsanity.com/paper/2202.02838/) (2022)
- [Data-centric Graph Learning: A Survey](https://mlsanity.com/paper/2310.04987/) (2023)
- [Deep Generative Model for Periodic Graphs](https://mlsanity.com/paper/2201.11932/) (2022)
- [Controllable Data Generation by Deep Learning: A Review](https://mlsanity.com/paper/2207.09542/) (2022)
- [A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptation](https://mlsanity.com/paper/2410.19265/) (2024)
- [ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splitting](https://mlsanity.com/paper/2205.13700/) (2022)
- [Disentangled Spatiotemporal Graph Generative Models](https://mlsanity.com/paper/2203.00411/) (2022)
- [FairGen: Towards Fair Graph Generation](https://mlsanity.com/paper/2303.17743/) (2023)
- [Multi-objective Deep Data Generation with Correlated Property Control](https://mlsanity.com/paper/2210.01796/) (2022)
- [Learning Disentangled Representations for Time Series](https://mlsanity.com/paper/2105.08179/) (2021)
- [A Primer on Temporal Graph Learning](https://mlsanity.com/paper/2401.03988/) (2024)
- [CCGG: A Deep Autoregressive Model for Class-Conditional Graph Generation](https://mlsanity.com/paper/2110.03800/) (2021)
- [Overcoming Order in Autoregressive Graph Generation](https://mlsanity.com/paper/2402.03387/) (2024)
- [Causal invariant geographic network representations with feature and structural distribution shifts](https://mlsanity.com/paper/2503.19382/) (2025)
- [Evolving Graph Learning for Out-of-Distribution Generalization in Non-stationary Environments](https://mlsanity.com/paper/2511.02354/) (2025)
- [Recovering Barab'asi-Albert Parameters of Graphs through Disentanglement](https://mlsanity.com/paper/2105.00997/) (2021)
- [Disentangled Causal Graph Learning for Online Unsupervised Root Cause Analysis](https://mlsanity.com/paper/2305.10638/) (2023)
- [SE-VGAE: Unsupervised Disentangled Representation Learning for Interpretable Architectural Layout Design Graph Generation](https://mlsanity.com/paper/2406.17418/) (2024)
- [Disentangled Graph Representation Based on Substructure-Aware Graph Optimal Matching Kernel Convolutional Networks](https://mlsanity.com/paper/2504.16360/) (2025)
- [NGTM: Substructure-based Neural Graph Topic Model for Interpretable Graph Generation](https://mlsanity.com/paper/2507.13133/) (2025)

## Abstract (arXiv)

Disentangled representation learning has recently attracted a significant amount of attention, particularly in the field of image representation learning. However, learning the disentangled representations behind a graph remains largely unexplored, especially for the attributed graph with both node and edge features. Disentanglement learning for graph generation has substantial new challenges including 1) the lack of graph deconvolution operations to jointly decode node and edge attributes; and 2) the difficulty in enforcing the disentanglement among latent factors that respectively influence: i) only nodes, ii) only edges, and iii) joint patterns between them. To address these challenges, we propose a new disentanglement enhancement framework for deep generative models for attributed graphs. In particular, a novel variational objective is proposed to disentangle the above three types of latent factors, with novel architecture for node and edge deconvolutions. Moreover, within each type, individual-factor-wise disentanglement is further enhanced, which is shown to be a generalization of the existing framework for images. Qualitative and quantitative experiments on both synthetic and real-world datasets demonstrate the effectiveness of the proposed model and its extensions.