paper-with-me

홈 › Papers

Marked Neural Spatio-Temporal Point Process Involving a Dynamic Graph Neural Network

2022-06-07 · Alice Moallemy-Oureh, Silvia Beddar-Wiesing, Yannick Nagel, Rüdiger Nather, Josephine M. Thomas

Temporal Point Processes (TPPs) have recently become increasingly interesting for learning dynamics in graph data. A reason for this is that learning on dynamic graph data is becoming more relevant, since data from many scientific fields, ranging from mathematics, biology, social sciences, and physics to computer science, is naturally related and inherently dynamic. In addition, TPPs provide a meaningful characterization of event streams and a prediction mechanism for future events. Therefore, (semi-)parameterized Neural TPPs have been introduced whose characterization can be (partially) learned and, thus, enable the representation of more complex phenomena. However, the research on modeling dynamic graphs with TPPs is relatively young, and only a few models for node attribute changes or evolving edges have been proposed yet. To allow for learning on fully dynamic graph streams, i.e., graphs that can change in their structure (addition/deletion of nodes/edge) and in their node/edge attributes, we propose a Marked Neural Spatio-Temporal Point Process (MNSTPP). It leverages a Dynamic Graph Neural Network to learn a Marked TPP that handles attributes and spatial data to model and predict any event in a graph stream.

📄 PDF Abstract BibTeX arXiv:2206.03469

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeGraph Neural NetworkPoint Processes

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음

Similar Papers 제목 키워드 기반

Transformer-Based Neural Marked Spatio Temporal Point Process Model for Football Match Events Analysis

2023-02-18 · Calvin C. K. Yeung, Tony Sit, Keisuke Fujii

With recently available football match event data that record the details of football matches, analysts and researchers have a great opportunity to develop new performance metrics, gain insight, and evaluate key performa…

Point Processes

Decoupled Learning for Factorial Marked Temporal Point Processes

2018-01-21 · Weichang Wu, Junchi Yan, Xiaokang Yang, Hongyuan Zha

This paper introduces the factorial marked temporal point process model and presents efficient learning methods. In conventional (multi-dimensional) marked temporal point process models, event is often encoded by a singl…

Point Processes

Score Matching-based Pseudolikelihood Estimation of Neural Marked Spatio-Temporal Point Process with Uncertainty Quantification

2023-10-25 · Zichong Li, Qunzhi Xu, Zhenghao Xu, Yajun Mei 외

Spatio-temporal point processes (STPPs) are potent mathematical tools for modeling and predicting events with both temporal and spatial features. Despite their versatility, most existing methods for learning STPPs either…

Point ProcessesUncertainty Quantification

AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning

2021-03-30 · CVPR 2021 1 · Madeleine Grunde-McLaughlin, Ranjay Krishna, Maneesh Agrawala

Visual events are a composition of temporal actions involving actors spatially interacting with objects. When developing computer vision models that can reason about compositional spatio-temporal events, we need benchmar…

Question AnsweringVideo Question AnsweringVisual Reasoning

A Spatio-Temporal Point Process for Fine-Grained Modeling of Reading Behavior

2025-06-24 · Francesco Ignazio Re, Andreas Opedal, Glib Manaiev, Mario Giulianelli 외

Reading is a process that unfolds across space and time, alternating between fixations where a reader focuses on a specific point in space, and saccades where a reader rapidly shifts their focus to a new point. An ansatz…