Structured Neural Marked Point Processes for Interpretable Event Interaction Modeling

• URL: http://arxiv.org/abs/2605.17568v2
• Date: Tue, 19 May 2026 19:36:29 GMT
• Title: Structured Neural Marked Point Processes for Interpretable Event Interaction Modeling
• Abstract summary: Multi-class event streams arise in numerous real-world applications, where uncovering structured, interpretable inter-event relationships, together with accurate prediction, remains a central challenge.<n>Existing neural point process models are highly expressive but encode event interactions in a black-box manner, preventing explicit discovery of structured dependencies.<n>We propose a structured neural marked point process (SNMPP) that achieves high modeling flexibility while enabling explicit event-wise and class-wise relationship discovery from data.
• Score: 12.453735847515006
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-class event streams arise in numerous real-world applications, where uncovering structured, interpretable inter-event relationships, together with accurate prediction, remains a central challenge. Existing neural point process models are highly expressive but encode event interactions in a black-box manner, preventing explicit discovery of structured dependencies. In this paper, we propose a structured neural marked point process (SNMPP) that achieves high modeling flexibility while enabling explicit event-wise and class-wise relationship discovery from data. Our model constructs a product-form neural influence kernel composed of a signed interaction network over event types and a delay-aware monotonic temporal network. This design enables explicit characterization of inter-class influence topology -- including excitation, inhibition, and neutrality -- while flexibly capturing diverse temporal decay patterns and potential influence delays. For efficient learning, we develop a stratified Monte Carlo estimator for stochastic training. Extensive experiments on synthetic and real-world benchmark datasets validate the ability of our approach to uncover structured relationships and deliver strong predictive performance.

Related papers

• Explaining Temporal Graph Neural Networks via Feature-induced Information Flow [20.91154042249583]
  Event-based Temporal Graph Neural Networks (ETGNNs) have demonstrated strong performance across a wide range of applications.<n>We propose a novel attribution method that analyzes the emphentire information flow through all event-associated variables.<n>We evaluate our approach on two synthetic datasets for epidemic tracing and social dynamics, as well as a real-world dataset of political event networks.
  arXiv  Detail & Related papers  (2026-06-25T16:00:11Z)
• Kronecker-Structured Nonparametric Spatiotemporal Point Processes [15.067976522057933]
  Eventstemporal domains arise in numerous real-world applications, where accurate prediction is a challenge.<n>We propose a Kronecker-Structuredpatio Stemporal Point Point (KSTPP) that enables transparent event-wise relationship discovery.
  arXiv  Detail & Related papers  (2026-03-24T22:13:24Z)
• Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction [57.19302613163439]
  We introduce neural network reprogrammability as a unifying framework for model adaptation.<n>We present a taxonomy that categorizes such information manipulation approaches across four key dimensions.<n>We also analyze remaining technical challenges and ethical considerations.
  arXiv  Detail & Related papers  (2025-06-05T05:42:27Z)
• Deep spatio-temporal point processes: Advances and new directions [20.673680115163425]
  Stemporal-temporal point processes (STPPs) model discrete events distributed in time and space.<n>Recent innovations integrate deep neural architectures, either by modeling the conditional intensity function directly or by learning flexible, data-driven influence kernels.<n>This article reviews the development of the deep influence kernel approach, which enjoys statistical explainability.
  arXiv  Detail & Related papers  (2025-04-08T18:28:12Z)
• Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond [61.18736646013446]
  In pursuit of a deeper understanding of its surprising behaviors, we investigate the utility of a simple yet accurate model of a trained neural network. Across three case studies, we illustrate how it can be applied to derive new empirical insights on a diverse range of prominent phenomena.
  arXiv  Detail & Related papers  (2024-10-31T22:54:34Z)
• Decoupled Marked Temporal Point Process using Neural Ordinary Differential Equations [14.828081841581296]
  A Marked Temporal Point Process (MTPP) is a process whose realization is a set of event-time data. Recent studies have utilized deep neural networks to capture complex temporal dependencies of events. We propose a Decoupled MTPP framework that disentangles characterization of a process into a set of evolving influences from different events.
  arXiv  Detail & Related papers  (2024-06-10T10:15:32Z)
• Cumulative Distribution Function based General Temporal Point Processes [49.758080415846884]
  CuFun model represents a novel approach to TPPs that revolves around the Cumulative Distribution Function (CDF) Our approach addresses several critical issues inherent in traditional TPP modeling. Our contributions encompass the introduction of a pioneering CDF-based TPP model, the development of a methodology for incorporating past event information into future event prediction.
  arXiv  Detail & Related papers  (2024-02-01T07:21:30Z)
• Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at Scale [54.15522908057831]
  We propose an adapted version of the computationally-Mixer for STTD forecast at scale. Our results surprisingly show that this simple-yeteffective solution can rival SOTA baselines when tested on several traffic benchmarks. Our findings contribute to the exploration of simple-yet-effective models for real-world STTD forecasting.
  arXiv  Detail & Related papers  (2023-07-04T05:19:19Z)
• An Empirical Study: Extensive Deep Temporal Point Process [61.14164208094238]
  We first review recent research emphasis and difficulties in modeling asynchronous event sequences with deep temporal point process.<n>We propose a Granger causality discovery framework for exploiting the relations among multi-types of events.
  arXiv  Detail & Related papers  (2021-10-19T10:15:00Z)
• Learning Neural Causal Models with Active Interventions [83.44636110899742]
  We introduce an active intervention-targeting mechanism which enables a quick identification of the underlying causal structure of the data-generating process. Our method significantly reduces the required number of interactions compared with random intervention targeting. We demonstrate superior performance on multiple benchmarks from simulated to real-world data.
  arXiv  Detail & Related papers  (2021-09-06T13:10:37Z)
• Deep Structural Point Process for Learning Temporal Interaction Networks [7.288706620982159]
  A temporal interaction network consists of a series of chronological interactions between users and items. Previous methods fail to consider the structural information of temporal interaction networks and inevitably lead to sub-optimal results. We propose a novel Deep Structural Point Process termed as DSPP for learning temporal interaction networks.
  arXiv  Detail & Related papers  (2021-07-08T03:07:34Z)
• Network Diffusions via Neural Mean-Field Dynamics [52.091487866968286]
  We propose a novel learning framework for inference and estimation problems of diffusion on networks. Our framework is derived from the Mori-Zwanzig formalism to obtain an exact evolution of the node infection probabilities. Our approach is versatile and robust to variations of the underlying diffusion network models.
  arXiv  Detail & Related papers  (2020-06-16T18:45:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.