# Neural Datalog Through Time: Informed Temporal Modeling via Logical Specification

arXiv: https://arxiv.org/abs/2006.16723 · HTML: https://mlsanity.com/paper/2006.16723/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2020.

## Built on by (most cited first, 10 of 10)

- [Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook](https://mlsanity.com/paper/2310.10196/) (2023)
- [Transformer Embeddings of Irregularly Spaced Events and Their Participants](https://mlsanity.com/paper/2201.00044/) (2021)
- [EasyTPP: Towards Open Benchmarking Temporal Point Processes](https://mlsanity.com/paper/2307.08097/) (2023)
- [HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequences](https://mlsanity.com/paper/2210.01753/) (2022)
- [Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning](https://mlsanity.com/paper/2305.16646/) (2023)
- [Prompt-augmented Temporal Point Process for Streaming Event Sequence](https://mlsanity.com/paper/2310.04993/) (2023)
- [Decomposable Transformer Point Processes](https://mlsanity.com/paper/2409.18158/) (2024)
- [pix2rule: End-to-end Neuro-symbolic Rule Learning](https://mlsanity.com/paper/2106.07487/) (2021)
- [Efficient Semiring-Weighted Earley Parsing](https://mlsanity.com/paper/2307.02982/) (2023)
- [Movement Analytics: Current Status, Application to Manufacturing, and Future Prospects from an AI Perspective](https://mlsanity.com/paper/2210.01344/) (2022)

## Abstract (arXiv)

Learning how to predict future events from patterns of past events is difficult when the set of possible event types is large. Training an unrestricted neural model might overfit to spurious patterns. To exploit domain-specific knowledge of how past events might affect an event's present probability, we propose using a temporal deductive database to track structured facts over time. Rules serve to prove facts from other facts and from past events. Each fact has a time-varying state---a vector computed by a neural net whose topology is determined by the fact's provenance, including its experience of past events. The possible event types at any time are given by special facts, whose probabilities are neurally modeled alongside their states. In both synthetic and real-world domains, we show that neural probabilistic models derived from concise Datalog programs improve prediction by encoding appropriate domain knowledge in their architecture.