# Neuro-Symbolic Temporal Point Processes

arXiv: https://arxiv.org/abs/2406.03914 · HTML: https://mlsanity.com/paper/2406.03914/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 35 references that are in the map.
- First posted on arXiv 6 Jun 2024.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Transformer Hawkes Process](https://mlsanity.com/paper/2002.09291/) (2020)
- [Modeling The Intensity Function Of Point Process Via Recurrent Neural Networks](https://mlsanity.com/paper/1705.08982/) (2017)
- [Learning Granger Causality for Hawkes Processes](https://mlsanity.com/paper/1602.04511/) (2016)
- [Inductive Logic Programming via Differentiable Deep Neural Logic Networks](https://mlsanity.com/paper/1906.03523/) (2019)
- [Logical Rule Induction and Theory Learning Using Neural Theorem Proving](https://mlsanity.com/paper/1809.02193/) (2018)
- [Towards Neural Theorem Proving at Scale](https://mlsanity.com/paper/1807.08204/) (2018)
- [Unveiling Latent Causal Rules: A Temporal Point Process Approach for Abnormal Event Explanation](https://mlsanity.com/paper/2402.05946/) (2024)

## Built on by (most cited first, 6 of 6)

- [Neural Spatiotemporal Point Processes: Trends and Challenges](https://mlsanity.com/paper/2502.09341/) (2025)
- [Neuro-Symbolic Artificial Intelligence: A Task-Directed Survey in the Black-Box Models Era](https://mlsanity.com/paper/2603.03177/) (2026)
- [Interpretable Hybrid-Rule Temporal Point Processes](https://mlsanity.com/paper/2504.11344/) (2025)
- [Hyper Hawkes Processes: Interpretable Models of Marked Temporal Point Processes](https://mlsanity.com/paper/2511.01096/) (2025)
- [Enhancing Temporal Awareness in LLMs for Temporal Point Processes](https://mlsanity.com/paper/2601.00845/) (2025)
- [LTLZinc: a Benchmarking Framework for Continual Learning and Neuro-Symbolic Temporal Reasoning](https://mlsanity.com/paper/2507.17482/) (2025)

## Abstract (arXiv)

Our goal is to textitefficiently discover a compact set of temporal logic rules to explain irregular events of interest. We introduce a neural-symbolic rule induction framework within the temporal point process model. The negative log-likelihood is the loss that guides the learning, where the explanatory logic rules and their weights are learned end-to-end in a textitdifferentiable way. Specifically, predicates and logic rules are represented as textitvector embeddings, where the predicate embeddings are fixed and the rule embeddings are trained via gradient descent to obtain the most appropriate compositional representations of the predicate embeddings. To make the rule learning process more efficient and flexible, we adopt a textitsequential covering algorithm, which progressively adds rules to the model and removes the event sequences that have been explained until all event sequences have been covered. All the found rules will be fed back to the models for a final rule embedding and weight refinement. Our approach showcases notable efficiency and accuracy across synthetic and real datasets, surpassing state-of-the-art baselines by a wide margin in terms of efficiency.