# Learning Temporal Point Processes for Efficient Retrieval of Continuous Time Event Sequences

arXiv: https://arxiv.org/abs/2202.11485 · HTML: https://mlsanity.com/paper/2202.11485/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 64 references that are in the map.
- First posted on arXiv 17 Feb 2022.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces](https://mlsanity.com/paper/1805.10190/) (2018)
- [Soft-DTW: a Differentiable Loss Function for Time-Series](https://mlsanity.com/paper/1703.01541/) (2017)
- [Transformer Hawkes Process](https://mlsanity.com/paper/2002.09291/) (2020)
- [Graph Matching Networks for Learning the Similarity of Graph Structured Objects](https://mlsanity.com/paper/1904.12787/) (2019)
- [Intensity-Free Learning of Temporal Point Processes](https://mlsanity.com/paper/1909.12127/) (2019)
- [Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos](https://mlsanity.com/paper/1507.05738/) (2015)
- [Unconstrained Monotonic Neural Networks](https://mlsanity.com/paper/1908.05164/) (2019)
- [Wasserstein Learning of Deep Generative Point Process Models](https://mlsanity.com/paper/1705.08051/) (2017)
- [Imputing Missing Events in Continuous-Time Event Streams](https://mlsanity.com/paper/1905.05570/) (2019)
- [A review on distance based time series classification](https://mlsanity.com/paper/1806.04509/) (2018)
- [Differentiable Divergences Between Time Series](https://mlsanity.com/paper/2010.08354/) (2020)
- [Expecting to be HIP: Hawkes Intensity Processes for Social Media Popularity](https://mlsanity.com/paper/1602.06033/) (2016)
- [Fake News Mitigation via Point Process Based Intervention](https://mlsanity.com/paper/1703.07823/) (2017)
- [Learning and Forecasting Opinion Dynamics in Social Networks](https://mlsanity.com/paper/1506.05474/) (2015)
- [Region Invariant Normalizing Flows for Mobility Transfer](https://mlsanity.com/paper/2109.05738/) (2021)
- [Adversarial Permutation Guided Node Representations for Link Prediction](https://mlsanity.com/paper/2012.08974/) (2020)
- [Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator](https://mlsanity.com/paper/2005.10477/) (2020)
- [Matrix Profile XXII: Exact Discovery of Time Series Motifs under DTW](https://mlsanity.com/paper/2009.07907/) (2020)
- [Modeling Adoption and Usage of Competing Products](https://mlsanity.com/paper/1406.0516/) (2014)
- [Learning Registered Point Processes from Idiosyncratic Observations](https://mlsanity.com/paper/1710.01410/) (2017)

## Built on by (most cited first, 14 of 14)

- [Mobility-LLM: Learning Visiting Intentions and Travel Preferences from Human Mobility Data with Large Language Models](https://mlsanity.com/paper/2411.00823/) (2024)
- [ProActive: Self-Attentive Temporal Point Process Flows for Activity Sequences](https://mlsanity.com/paper/2206.05291/) (2022)
- [Retrieval of Temporal Event Sequences from Textual Descriptions](https://mlsanity.com/paper/2410.14043/) (2024)
- [Modeling Continuous Time Sequences with Intermittent Observations using Marked Temporal Point Processes](https://mlsanity.com/paper/2206.12414/) (2022)
- [Modeling Spatial Trajectories using Coarse-Grained Smartphone Logs](https://mlsanity.com/paper/2208.13775/) (2022)
- [Proactive Resource Request for Disaster Response: A Deep Learning-based Optimization Model](https://mlsanity.com/paper/2307.16661/) (2023)
- [Spatial-Temporal Cross-View Contrastive Pre-training for Check-in Sequence Representation Learning](https://mlsanity.com/paper/2407.15899/) (2024)
- [Retrieving Continuous Time Event Sequences using Neural Temporal Point Processes with Learnable Hashing](https://mlsanity.com/paper/2307.09613/) (2023)
- [Tapestry of Time and Actions: Modeling Human Activity Sequences using Temporal Point Process Flows](https://mlsanity.com/paper/2307.10305/) (2023)
- [Cumulative Distribution Function based General Temporal Point Processes](https://mlsanity.com/paper/2402.00388/) (2024)
- [Transfer Learning with Point Transformers](https://mlsanity.com/paper/2404.00846/) (2024)
- [Differentiable Adversarial Attacks for Marked Temporal Point Processes](https://mlsanity.com/paper/2501.10606/) (2025)
- [Can We Predict Your Next Move Without Breaking Your Privacy?](https://mlsanity.com/paper/2507.08843/) (2025)
- [GSTM-HMU: Generative Spatio-Temporal Modeling for Human Mobility Understanding](https://mlsanity.com/paper/2509.19135/) (2025)

## Abstract (arXiv)

Recent developments in predictive modeling using marked temporal point processes (MTPP) have enabled an accurate characterization of several real-world applications involving continuous-time event sequences (CTESs). However, the retrieval problem of such sequences remains largely unaddressed in literature. To tackle this, we propose NEUROSEQRET which learns to retrieve and rank a relevant set of continuous-time event sequences for a given query sequence, from a large corpus of sequences. More specifically, NEUROSEQRET first applies a trainable unwarping function on the query sequence, which makes it comparable with corpus sequences, especially when a relevant query-corpus pair has individually different attributes. Next, it feeds the unwarped query sequence and the corpus sequence into MTPP guided neural relevance models. We develop two variants of the relevance model which offer a tradeoff between accuracy and efficiency. We also propose an optimization framework to learn binary sequence embeddings from the relevance scores, suitable for the locality-sensitive hashing leading to a significant speedup in returning top-K results for a given query sequence. Our experiments with several datasets show the significant accuracy boost of NEUROSEQRET beyond several baselines, as well as the efficacy of our hashing mechanism.