# The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction

arXiv: https://arxiv.org/abs/2104.06344 · HTML: https://mlsanity.com/paper/2104.06344/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 56 references that are in the map.
- First posted on arXiv 13 Apr 2021.

## Builds on (most cited first, 26 of 26)

- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models](https://mlsanity.com/paper/1802.08773/) (2018)
- [GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders](https://mlsanity.com/paper/1802.03480/) (2018)
- [GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation](https://mlsanity.com/paper/2001.09382/) (2020)
- [Efficient Graph Generation with Graph Recurrent Attention Networks](https://mlsanity.com/paper/1910.00760/) (2019)
- [Learning Deep Generative Models of Graphs](https://mlsanity.com/paper/1803.03324/) (2018)
- [Incorporating Copying Mechanism in Sequence-to-Sequence Learning](https://mlsanity.com/paper/1603.06393/) (2016)
- [Graphite: Iterative Generative Modeling of Graphs](https://mlsanity.com/paper/1803.10459/) (2018)
- [Graph Normalizing Flows](https://mlsanity.com/paper/1905.13177/) (2019)
- [Reasoning about Goals, Steps, and Temporal Ordering with WikiHow](https://mlsanity.com/paper/2009.07690/) (2020)
- [Scalable Deep Generative Modeling for Sparse Graphs](https://mlsanity.com/paper/2006.15502/) (2020)
- [Constructing Narrative Event Evolutionary Graph for Script Event Prediction](https://mlsanity.com/paper/1805.05081/) (2018)
- [An Improved Neural Baseline for Temporal Relation Extraction](https://mlsanity.com/paper/1909.00429/) (2019)
- [Causal Inference of Script Knowledge](https://mlsanity.com/paper/2004.01174/) (2020)
- [Event Representations with Tensor-based Compositions](https://mlsanity.com/paper/1711.07611/) (2017)
- [Probabilistic Frame Induction](https://mlsanity.com/paper/1302.4813/) (2013)
- [A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolution](https://mlsanity.com/paper/2104.01697/) (2021)
- [Joint Learning Templates and Slots for Event Schema Induction](https://mlsanity.com/paper/1603.01333/) (2016)
- [InScript: Narrative texts annotated with script information](https://mlsanity.com/paper/1703.05260/) (2017)
- [Sequence to Sequence Learning for Event Prediction](https://mlsanity.com/paper/1709.06033/) (2017)
- [Two Discourse Driven Language Models for Semantics](https://mlsanity.com/paper/1606.05679/) (2016)
- [Modeling Preconditions in Text with a Crowd-sourced Dataset](https://mlsanity.com/paper/2010.02429/) (2020)
- [Graph-Aware Transformer: Is Attention All Graphs Need?](https://mlsanity.com/paper/2006.05213/) (2020)

## Built on by (most cited first, 30 of 40)

- [Large Language Models on Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2312.02783/) (2023)
- [Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning](https://mlsanity.com/paper/2205.01376/) (2022)
- [Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding](https://mlsanity.com/paper/2406.02472/) (2024)
- [Open-Domain Hierarchical Event Schema Induction by Incremental Prompting and Verification](https://mlsanity.com/paper/2307.01972/) (2023)
- [Extracting Temporal Event Relation with Syntax-guided Graph Transformer](https://mlsanity.com/paper/2104.09570/) (2021)
- [Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction](https://mlsanity.com/paper/2210.04992/) (2022)
- [Human-in-the-Loop Schema Induction](https://mlsanity.com/paper/2302.13048/) (2023)
- [Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning](https://mlsanity.com/paper/2305.14970/) (2023)
- [Multimedia Generative Script Learning for Task Planning](https://mlsanity.com/paper/2208.12306/) (2022)
- [Open-Vocabulary Argument Role Prediction for Event Extraction](https://mlsanity.com/paper/2211.01577/) (2022)
- [OpenEP: Open-Ended Future Event Prediction](https://mlsanity.com/paper/2408.06578/) (2024)
- [Zero-Shot On-the-Fly Event Schema Induction](https://mlsanity.com/paper/2210.06254/) (2022)
- [SmartBook: AI-Assisted Situation Report Generation for Intelligence Analysts](https://mlsanity.com/paper/2303.14337/) (2023)
- [A Comprehensive Evaluation of Large Language Models on Temporal Event Forecasting](https://mlsanity.com/paper/2407.11638/) (2024)
- [Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces](https://mlsanity.com/paper/2511.07587/) (2025)
- [Harvesting Event Schemas from Large Language Models](https://mlsanity.com/paper/2305.07280/) (2023)
- [Drafting Event Schemas using Language Models](https://mlsanity.com/paper/2305.14847/) (2023)
- [EvEval: A Comprehensive Evaluation of Event Semantics for Large Language Models](https://mlsanity.com/paper/2305.15268/) (2023)
- [LOGOS: LLM-driven End-to-End Grounded Theory Development and Schema Induction for Qualitative Research](https://mlsanity.com/paper/2509.24294/) (2025)
- [POQue: Asking Participant-specific Outcome Questions for a Deeper Understanding of Complex Events](https://mlsanity.com/paper/2212.02629/) (2022)
- [Schema-Guided Event Graph Completion](https://mlsanity.com/paper/2206.02921/) (2022)
- [Non-Sequential Graph Script Induction via Multimedia Grounding](https://mlsanity.com/paper/2305.17542/) (2023)
- [Temporal Relation Extraction in Clinical Texts: A Span-based Graph Transformer Approach](https://mlsanity.com/paper/2503.18085/) (2025)
- [Open-Domain Event Graph Induction for Mitigating Framing Bias](https://mlsanity.com/paper/2305.12835/) (2023)
- [A Diffusion Model for Event Skeleton Generation](https://mlsanity.com/paper/2305.17458/) (2023)
- [We are what we repeatedly do: Inducing and deploying habitual schemas in persona-based responses](https://mlsanity.com/paper/2310.06245/) (2023)
- [Creating an AI Observer: Generative Semantic Workspaces](https://mlsanity.com/paper/2406.04555/) (2024)
- [A Survey on Event Prediction Methods from a Systems Perspective: Bringing Together Disparate Research Areas](https://mlsanity.com/paper/2302.04018/) (2023)
- [SCTc-TE: A Comprehensive Formulation and Benchmark for Temporal Event Forecasting](https://mlsanity.com/paper/2312.01052/) (2023)
- [LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World](https://mlsanity.com/paper/2506.00980/) (2025)

## Abstract (arXiv)

Event schemas encode knowledge of stereotypical structures of events and their connections. As events unfold, schemas are crucial to act as a scaffolding. Previous work on event schema induction focuses either on atomic events or linear temporal event sequences, ignoring the interplay between events via arguments and argument relations. We introduce a new concept of Temporal Complex Event Schema: a graph-based schema representation that encompasses events, arguments, temporal connections and argument relations. In addition, we propose a Temporal Event Graph Model that predicts event instances following the temporal complex event schema. To build and evaluate such schemas, we release a new schema learning corpus containing 6,399 documents accompanied with event graphs, and we have manually constructed gold-standard schemas. Intrinsic evaluations based on schema matching and instance graph perplexity, prove the superior quality of our probabilistic graph schema library compared to linear representations. Extrinsic evaluation on schema-guided future event prediction further demonstrates the predictive power of our event graph model, significantly outperforming human schemas and baselines by more than 23.8% on HITS@1.