# Mitigating Performance Saturation in Neural Marked Point Processes: Architectures and Loss Functions

arXiv: https://arxiv.org/abs/2107.03354 · HTML: https://mlsanity.com/paper/2107.03354/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 39 references that are in the map.
- First posted on arXiv 7 Jul 2021.

## Builds on (most cited first, 15 of 15)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Deep Double Descent: Where Bigger Models and More Data Hurt](https://mlsanity.com/paper/1912.02292/) (2019)
- [Transformer Hawkes Process](https://mlsanity.com/paper/2002.09291/) (2020)
- [Fully Neural Network based Model for General Temporal Point Processes](https://mlsanity.com/paper/1905.09690/) (2019)
- [Modeling The Intensity Function Of Point Process Via Recurrent Neural Networks](https://mlsanity.com/paper/1705.08982/) (2017)
- [Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks](https://mlsanity.com/paper/1704.06803/) (2017)
- [Learning Granger Causality for Hawkes Processes](https://mlsanity.com/paper/1602.04511/) (2016)
- [A Review of Self-Exciting Spatio-Temporal Point Processes and Their Applications](https://mlsanity.com/paper/1708.02647/) (2017)
- [Uncovering Causality from Multivariate Hawkes Integrated Cumulants](https://mlsanity.com/paper/1607.06333/) (2016)
- [Discovering Latent Network Structure in Point Process Data](https://mlsanity.com/paper/1402.0914/) (2014)
- [Fake News Mitigation via Point Process Based Intervention](https://mlsanity.com/paper/1703.07823/) (2017)
- [Self-Attentive Hawkes Processes](https://mlsanity.com/paper/1907.07561/) (2019)
- [A Dirichlet Mixture Model of Hawkes Processes for Event Sequence Clustering](https://mlsanity.com/paper/1701.09177/) (2017)
- [Superposition-Assisted Stochastic Optimization for Hawkes Processes](https://mlsanity.com/paper/1802.04725/) (2018)

## Built on by (most cited first, 12 of 12)

- [Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification](https://mlsanity.com/paper/2312.07338/) (2023)
- [Enhancing Asynchronous Time Series Forecasting with Contrastive Relational Inference](https://mlsanity.com/paper/2309.02868/) (2023)
- [Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter](https://mlsanity.com/paper/2309.09443/) (2023)
- [GMTR: Graph Matching Transformers](https://mlsanity.com/paper/2311.08141/) (2023)
- [DarkShot: Lighting Dark Images with Low-Compute and High-Quality](https://mlsanity.com/paper/2312.16805/) (2023)
- [TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processing](https://mlsanity.com/paper/2401.05431/) (2024)
- [TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networks](https://mlsanity.com/paper/2401.05432/) (2024)
- [T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Image](https://mlsanity.com/paper/2403.13663/) (2024)
- [Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithms](https://mlsanity.com/paper/2408.17101/) (2024)
- [Towards General Deepfake Detection with Dynamic Curriculum](https://mlsanity.com/paper/2410.11162/) (2024)
- [Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphs](https://mlsanity.com/paper/2410.13409/) (2024)
- [Mask6D: Masked Pose Priors For 6D Object Pose Estimation](https://mlsanity.com/paper/2507.06486/) (2025)

## Abstract (arXiv)

Attributed event sequences are commonly encountered in practice. A recent research line focuses on incorporating neural networks with the statistical model -- marked point processes, which is the conventional tool for dealing with attributed event sequences. Neural marked point processes possess good interpretability of probabilistic models as well as the representational power of neural networks. However, we find that performance of neural marked point processes is not always increasing as the network architecture becomes more complicated and larger, which is what we call the performance saturation phenomenon. This is due to the fact that the generalization error of neural marked point processes is determined by both the network representational ability and the model specification at the same time. Therefore we can draw two major conclusions: first, simple network structures can perform no worse than complicated ones for some cases; second, using a proper probabilistic assumption is as equally, if not more, important as improving the complexity of the network. Based on this observation, we propose a simple graph-based network structure called GCHP, which utilizes only graph convolutional layers, thus it can be easily accelerated by the parallel mechanism. We directly consider the distribution of interarrival times instead of imposing a specific assumption on the conditional intensity function, and propose to use a likelihood ratio loss with a moment matching mechanism for optimization and model selection. Experimental results show that GCHP can significantly reduce training time and the likelihood ratio loss with interarrival time probability assumptions can greatly improve the model performance.