ITPP: Learning Disentangled Event Dynamics in Marked Temporal Point Processes

📝 Original Info

• Title: ITPP: Learning Disentangled Event Dynamics in Marked Temporal Point Processes
• ArXiv ID: 2511.06032
• Date: 2025-11-08
• Authors: ** 정보가 제공되지 않았습니다. (논문 원문 혹은 DOI를 확인해 주세요.) **

📝 Abstract

Marked Temporal Point Processes (MTPPs) provide a principled framework for modeling asynchronous event sequences by conditioning on the history of past events. However, most existing MTPP models rely on channel-mixing strategies that encode information from different event types into a single, fixed-size latent representation. This entanglement can obscure type-specific dynamics, leading to performance degradation and increased risk of overfitting. In this work, we introduce ITPP, a novel channel-independent architecture for MTPP modeling that decouples event type information using an encoder-decoder framework with an ODE-based backbone. Central to ITPP is a type-aware inverted self-attention mechanism, designed to explicitly model inter-channel correlations among heterogeneous event types. This architecture enhances effectiveness and robustness while reducing overfitting. Comprehensive experiments on multiple real-world and synthetic datasets demonstrate that ITPP consistently outperforms state-of-the-art MTPP models in both predictive accuracy and generalization.

💡 Deep Analysis

📄 Full Content

Reference