# Disentangled Dynamic Graph Deep Generation

arXiv: https://arxiv.org/abs/2010.07276 · HTML: https://mlsanity.com/paper/2010.07276/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2020.

## Built on by (most cited first, 27 of 27)

- [A Survey on Deep Graph Generation: Methods and Applications](https://mlsanity.com/paper/2203.06714/) (2022)
- [FARF: A Fair and Adaptive Random Forests Classifier](https://mlsanity.com/paper/2108.07403/) (2021)
- [Longitudinal Fairness with Censorship](https://mlsanity.com/paper/2203.16024/) (2022)
- [Fairness Amidst Non-IID Graph Data: A Literature Review](https://mlsanity.com/paper/2202.07170/) (2022)
- [Fair Decision-making Under Uncertainty](https://mlsanity.com/paper/2301.12364/) (2023)
- [LSTM Based Sentiment Analysis for Cryptocurrency Prediction](https://mlsanity.com/paper/2103.14804/) (2021)
- [Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory](https://mlsanity.com/paper/2107.01671/) (2021)
- [Interpretable Visual Understanding with Cognitive Attention Network](https://mlsanity.com/paper/2108.02924/) (2021)
- [Individual Fairness under Uncertainty](https://mlsanity.com/paper/2302.08015/) (2023)
- [Digital Forensics in the Age of Large Language Models](https://mlsanity.com/paper/2504.02963/) (2025)
- [Incremental Mining of Frequent Serial Episodes Considering Multiple Occurrences](https://mlsanity.com/paper/2201.11650/) (2022)
- [Generative AI in Depth: A Survey of Recent Advances, Model Variants, and Real-World Applications](https://mlsanity.com/paper/2510.21887/) (2025)
- [Responsibility Management through Responsibility Networks](https://mlsanity.com/paper/2102.07246/) (2021)
- [AI-Driven Healthcare: A Review on Ensuring Fairness and Mitigating Bias](https://mlsanity.com/paper/2407.19655/) (2024)
- [AMCR: A Framework for Assessing and Mitigating Copyright Risks in Generative Models](https://mlsanity.com/paper/2509.00641/) (2025)
- [Towards Transparent AI: A Survey on Explainable Language Models](https://mlsanity.com/paper/2509.21631/) (2025)
- [Geometric learning of the conformational dynamics of molecules using dynamic graph neural networks](https://mlsanity.com/paper/2106.13277/) (2021)
- [GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph Learning](https://mlsanity.com/paper/2507.03267/) (2025)
- [A Generic Knowledge Based Medical Diagnosis Expert System](https://mlsanity.com/paper/2110.04439/) (2021)
- [DBGDGM: Dynamic Brain Graph Deep Generative Model](https://mlsanity.com/paper/2301.11408/) (2023)
- [The Internet of Responsibilities-Connecting Human Responsibilities using Big Data and Blockchain](https://mlsanity.com/paper/2312.04729/) (2023)
- [Uncertain Boundaries: Multidisciplinary Approaches to Copyright Issues in Generative AI](https://mlsanity.com/paper/2404.08221/) (2024)
- [Fairness-Aware Graph Representation Learning with Limited Demographic Information](https://mlsanity.com/paper/2511.13540/) (2025)
- [Improving Specificity in Mammography Using Cross-correlation between Wavelet and Fourier Transform](https://mlsanity.com/paper/2201.08385/) (2022)
- [Attention Mechanism based Cognition-level Scene Understanding](https://mlsanity.com/paper/2204.08027/) (2022)
- [G2A2: An Automated Graph Generator with Attributes and Anomalies](https://mlsanity.com/paper/2210.07449/) (2022)
- [Synthesizing Diverse Network Flow Datasets with Scalable Dynamic Multigraph Generation](https://mlsanity.com/paper/2505.07777/) (2025)

## Abstract (arXiv)

Deep generative models for graphs have exhibited promising performance in ever-increasing domains such as design of molecules (i.e, graph of atoms) and structure prediction of proteins (i.e., graph of amino acids). Existing work typically focuses on static rather than dynamic graphs, which are actually very important in the applications such as protein folding, molecule reactions, and human mobility. Extending existing deep generative models from static to dynamic graphs is a challenging task, which requires to handle the factorization of static and dynamic characteristics as well as mutual interactions among node and edge patterns. Here, this paper proposes a novel framework of factorized deep generative models to achieve interpretable dynamic graph generation. Various generative models are proposed to characterize conditional independence among node, edge, static, and dynamic factors. Then, variational optimization strategies as well as dynamic graph decoders are proposed based on newly designed factorized variational autoencoders and recurrent graph deconvolutions. Extensive experiments on multiple datasets demonstrate the effectiveness of the proposed models.