# Time-Dependent Representation for Neural Event Sequence Prediction

arXiv: https://arxiv.org/abs/1708.00065 · HTML: https://mlsanity.com/paper/1708.00065/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2017.

## Built on by (most cited first, 11 of 11)

- [A Review of Location Encoding for GeoAI: Methods and Applications](https://mlsanity.com/paper/2111.04006/) (2021)
- [CEHR-GPT: Generating Electronic Health Records with Chronological Patient Timelines](https://mlsanity.com/paper/2402.04400/) (2024)
- [A Survey on Deep Learning Techniques for Action Anticipation](https://mlsanity.com/paper/2309.17257/) (2023)
- [Modeling Events and Interactions through Temporal Processes -- A Survey](https://mlsanity.com/paper/2303.06067/) (2023)
- [Review of Video Predictive Understanding: Early Action Recognition and Future Action Prediction](https://mlsanity.com/paper/2107.05140/) (2021)
- [CEHR-XGPT: A Scalable Multi-Task Foundation Model for Electronic Health Records](https://mlsanity.com/paper/2509.03643/) (2025)
- [A Temporal Kernel Approach for Deep Learning with Continuous-time Information](https://mlsanity.com/paper/2103.15213/) (2021)
- [Pre-training Contextual Location Embeddings in Personal Trajectories via Efficient Hierarchical Location Representations](https://mlsanity.com/paper/2310.01252/) (2023)
- [Hybrid Model with Time Modeling for Sequential Recommender Systems](https://mlsanity.com/paper/2103.06138/) (2021)
- [Rethinking Time Encoding via Learnable Transformation Functions](https://mlsanity.com/paper/2505.00887/) (2025)
- [Recursive input and state estimation: A general framework for learning from time series with missing data](https://mlsanity.com/paper/2104.08556/) (2021)

## Abstract (arXiv)

Existing sequence prediction methods are mostly concerned with time-independent sequences, in which the actual time span between events is irrelevant and the distance between events is simply the difference between their order positions in the sequence. While this time-independent view of sequences is applicable for data such as natural languages, e.g., dealing with words in a sentence, it is inappropriate and inefficient for many real world events that are observed and collected at unequally spaced points of time as they naturally arise, e.g., when a person goes to a grocery store or makes a phone call. The time span between events can carry important information about the sequence dependence of human behaviors. In this work, we propose a set of methods for using time in sequence prediction. Because neural sequence models such as RNN are more amenable for handling token-like input, we propose two methods for time-dependent event representation, based on the intuition on how time is tokenized in everyday life and previous work on embedding contextualization. We also introduce two methods for using next event duration as regularization for training a sequence prediction model. We discuss these methods based on recurrent neural nets. We evaluate these methods as well as baseline models on five datasets that resemble a variety of sequence prediction tasks. The experiments revealed that the proposed methods offer accuracy gain over baseline models in a range of settings.