# A Diffusion Model for Event Skeleton Generation

arXiv: https://arxiv.org/abs/2305.17458 · HTML: https://mlsanity.com/paper/2305.17458/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 14 of its 27 references that are in the map.
- First posted on arXiv 27 May 2023.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 14 of 14)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [D-VAE: A Variational Autoencoder for Directed Acyclic Graphs](https://mlsanity.com/paper/1904.11088/) (2019)
- [Vision-and-Language Pretrained Models: A Survey](https://mlsanity.com/paper/2204.07356/) (2022)
- [The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction](https://mlsanity.com/paper/2104.06344/) (2021)
- [DensePure: Understanding Diffusion Models towards Adversarial Robustness](https://mlsanity.com/paper/2211.00322/) (2022)
- [PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognition](https://mlsanity.com/paper/2208.09801/) (2022)
- [Probabilistic Frame Induction](https://mlsanity.com/paper/1302.4813/) (2013)
- [Mask-then-Fill: A Flexible and Effective Data Augmentation Framework for Event Extraction](https://mlsanity.com/paper/2301.02427/) (2023)
- [Improving Event Representation via Simultaneous Weakly Supervised Contrastive Learning and Clustering](https://mlsanity.com/paper/2203.07633/) (2022)
- [Joint Learning Templates and Slots for Event Schema Induction](https://mlsanity.com/paper/1603.01333/) (2016)
- [A Generative Approach for Script Event Prediction via Contrastive Fine-tuning](https://mlsanity.com/paper/2212.03496/) (2022)
- [Progressive Open-Domain Response Generation with Multiple Controllable Attributes](https://mlsanity.com/paper/2106.14614/) (2021)

## Built on by (most cited first, 3 of 3)

- [Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding](https://mlsanity.com/paper/2406.02472/) (2024)
- [Learning to Describe for Predicting Zero-shot Drug-Drug Interactions](https://mlsanity.com/paper/2403.08377/) (2024)
- [MoE-DiffuSeq: Enhancing Long-Document Diffusion Models with Sparse Attention and Mixture of Experts](https://mlsanity.com/paper/2512.20604/) (2025)

## Abstract (arXiv)

Event skeleton generation, aiming to induce an event schema skeleton graph with abstracted event nodes and their temporal relations from a set of event instance graphs, is a critical step in the temporal complex event schema induction task. Existing methods effectively address this task from a graph generation perspective but suffer from noise-sensitive and error accumulation, e.g., the inability to correct errors while generating schema. We, therefore, propose a novel Diffusion Event Graph Model~(DEGM) to address these issues. Our DEGM is the first workable diffusion model for event skeleton generation, where the embedding and rounding techniques with a custom edge-based loss are introduced to transform a discrete event graph into learnable latent representation. Furthermore, we propose a denoising training process to maintain the model's robustness. Consequently, DEGM derives the final schema, where error correction is guaranteed by iteratively refining the latent representation during the schema generation process. Experimental results on three IED bombing datasets demonstrate that our DEGM achieves better results than other state-of-the-art baselines. Our code and data are available at https://github.com/zhufq00/EventSkeletonGeneration.