{"ID":2844656,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.06032","arxiv_id":"2511.06032","title":"ITPP: Learning Disentangled Event Dynamics in Marked Temporal Point Processes","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.","short_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 represe...","url_abs":"https://arxiv.org/abs/2511.06032","url_pdf":"https://arxiv.org/pdf/2511.06032v1","authors":"[\"Wang-Tao Zhou\",\"Zhao Kang\",\"Ke Yan\",\"Ling Tian\"]","published":"2025-11-08T15:00:25Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}