# DyDiff-VAE: A Dynamic Variational Framework for Information Diffusion Prediction

arXiv: https://arxiv.org/abs/2106.03251 · HTML: https://mlsanity.com/paper/2106.03251/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2021.

## Built on by (most cited first, 18 of 18)

- [Graph Communal Contrastive Learning](https://mlsanity.com/paper/2110.14863/) (2021)
- [Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment](https://mlsanity.com/paper/2203.14987/) (2022)
- [Generalizing Graph ODE for Learning Complex System Dynamics across Environments](https://mlsanity.com/paper/2307.04287/) (2023)
- [Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphs](https://mlsanity.com/paper/2210.08654/) (2022)
- [A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware](https://mlsanity.com/paper/2306.14052/) (2023)
- [RETE: Retrieval-Enhanced Temporal Event Forecasting on Unified Query Product Evolutionary Graph](https://mlsanity.com/paper/2202.06129/) (2022)
- [Human Mobility Modeling During the COVID-19 Pandemic via Deep Graph Diffusion Infomax](https://mlsanity.com/paper/2212.05707/) (2022)
- [Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs](https://mlsanity.com/paper/2307.01933/) (2023)
- [Geometry-Preserving Encoder/Decoder in Latent Generative Models](https://mlsanity.com/paper/2501.09876/) (2025)
- [Mutually-paced Knowledge Distillation for Cross-lingual Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2303.14898/) (2023)
- [Two-stage Denoising Diffusion Model for Source Localization in Graph Inverse Problems](https://mlsanity.com/paper/2304.08841/) (2023)
- [Noisy Positive-Unlabeled Learning with Self-Training for Speculative Knowledge Graph Reasoning](https://mlsanity.com/paper/2306.07512/) (2023)
- [SudokuSens: Enhancing Deep Learning Robustness for IoT Sensing Applications using a Generative Approach](https://mlsanity.com/paper/2402.02275/) (2024)
- [AutoCas: Autoregressive Cascade Predictor in Social Networks via Large Language Models](https://mlsanity.com/paper/2502.18040/) (2025)
- [Synergistic Signals: Exploiting Co-Engagement and Semantic Links via Graph Neural Networks](https://mlsanity.com/paper/2312.04071/) (2023)
- [CasFT: Future Trend Modeling for Information Popularity Prediction with Dynamic Cues-Driven Diffusion Models](https://mlsanity.com/paper/2409.16619/) (2024)
- [On Your Mark, Get Set, Predict! Modeling Continuous-Time Dynamics of Cascades for Information Popularity Prediction](https://mlsanity.com/paper/2409.16623/) (2024)
- [SCRAG: Social Computing-Based Retrieval Augmented Generation for Community Response Forecasting in Social Media Environments](https://mlsanity.com/paper/2504.16947/) (2025)

## Abstract (arXiv)

This paper describes a novel diffusion model, DyDiff-VAE, for information diffusion prediction on social media. Given the initial content and a sequence of forwarding users, DyDiff-VAE aims to estimate the propagation likelihood for other potential users and predict the corresponding user rankings. Inferring user interests from diffusion data lies the foundation of diffusion prediction, because users often forward the information in which they are interested or the information from those who share similar interests. Their interests also evolve over time as the result of the dynamic social influence from neighbors and the time-sensitive information gained inside/outside the social media. Existing works fail to model users' intrinsic interests from the diffusion data and assume user interests remain static along the time. DyDiff-VAE advances the state of the art in two directions: (i) We propose a dynamic encoder to infer the evolution of user interests from observed diffusion data. (ii) We propose a dual attentive decoder to estimate the propagation likelihood by integrating information from both the initial cascade content and the forwarding user sequence. Extensive experiments on four real-world datasets from Twitter and Youtube demonstrate the advantages of the proposed model; we show that it achieves 43.3% relative gains over the best baseline on average. Moreover, it has the lowest run-time compared with recurrent neural network based models.