A Deep Probabilistic Framework for Continuous Time Dynamic Graph Generation

2024-12-20 · Ryien Hosseini, Filippo Simini, Venkatram Vishwanath, Henry Hoffmann

Recent advancements in graph representation learning have shifted attention towards dynamic graphs, which exhibit evolving topologies and features over time. The increased use of such graphs creates a paramount need for generative models suitable for applications such as data augmentation, obfuscation, and anomaly detection. However, there are few generative techniques that handle continuously changing temporal graph data; existing work largely relies on augmenting static graphs with additional temporal information to model dynamic interactions between nodes. In this work, we propose a fundamentally different approach: We instead directly model interactions as a joint probability of an edge forming between two nodes at a given time. This allows us to autoregressively generate new synthetic dynamic graphs in a largely assumption free, scalable, and inductive manner. We formalize this approach as DG-Gen, a generative framework for continuous time dynamic graphs, and demonstrate its effectiveness over five datasets. Our experiments demonstrate that DG-Gen not only generates higher fidelity graphs compared to traditional methods but also significantly advances link prediction tasks.

📄 PDF Abstract BibTeX arXiv:2412.15582

Code (1)

ryienh/dggen 공식 구현 pytorch

Tasks

Anomaly Detection Data Augmentation Graph Generation Graph Representation Learning Link Prediction Representation Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Attention 설명 없음

GOPHER: Categorical probabilistic forecasting withgraph structure via local continuous-time dynamics

2021-09-22 · NeurIPS Workshop ICBINB 2021 12 · Ke Alexander Wang, Danielle C. Maddix, Bernie Wang

We consider the problem of probabilistic forecasting over categories with graph structure, where the dynamics at a vertex depends on its local connectivity structure. We present GOPHER, a method that combines the inducti…

Inductive Bias

GOPHER: Categorical probabilistic forecasting with graph structure via local continuous-time dynamics

2021-12-18 · Ke Alexander Wang, Danielle Maddix, Yuyang Wang

Inductive Bias

ProGen: Revisiting Probabilistic Spatial-Temporal Time Series Forecasting from a Continuous Generative Perspective Using Stochastic Differential Equations

2024-11-02 · Mingze Gong, Lei Chen, Jia Li

Accurate forecasting of spatiotemporal data remains challenging due to complex spatial dependencies and temporal dynamics. The inherent uncertainty and variability in such data often render deterministic models insuffici…

Denoising Time Series Time Series Forecasting

Neural Continuous-Time Supermartingale Certificates

2024-12-23 · Grigory Neustroev, Mirco Giacobbe, Anna Lukina

We introduce for the first time a neural-certificate framework for continuous-time stochastic dynamical systems. Autonomous learning systems in the physical world demand continuous-time reasoning, yet existing learnable …

Probabilistic Pontryagin's Maximum Principle for Continuous-Time Model-Based Reinforcement Learning

2025-04-03 · David Leeftink, Çağatay Yıldız, Steffen Ridderbusch, Max Hinne 외

Without exact knowledge of the true system dynamics, optimal control of non-linear continuous-time systems requires careful treatment of epistemic uncertainty. In this work, we propose a probabilistic extension to Pontry…

Model-based Reinforcement Learning reinforcement-learning Reinforcement Learning