# Federated Neural Nonparametric Point Processes

arXiv: https://arxiv.org/abs/2410.05637 · HTML: https://mlsanity.com/paper/2410.05637/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 56 references that are in the map.
- First posted on arXiv 8 Oct 2024.

## Builds on (most cited first, 25 of 25)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Deep Kernel Learning](https://mlsanity.com/paper/1511.02222/) (2015)
- [Conditional Neural Processes](https://mlsanity.com/paper/1807.01613/) (2018)
- [Transformer Hawkes Process](https://mlsanity.com/paper/2002.09291/) (2020)
- [Neural Temporal Point Processes: A Review](https://mlsanity.com/paper/2104.03528/) (2021)
- [Personalized Federated Learning with Gaussian Processes](https://mlsanity.com/paper/2106.15482/) (2021)
- [Personalized Federated Learning via Variational Bayesian Inference](https://mlsanity.com/paper/2206.07977/) (2022)
- [EasyTPP: Towards Open Benchmarking Temporal Point Processes](https://mlsanity.com/paper/2307.08097/) (2023)
- [Sequential Neural Processes](https://mlsanity.com/paper/1906.10264/) (2019)
- [Neural Temporal Point Processes For Modelling Electronic Health Records](https://mlsanity.com/paper/2007.13794/) (2020)
- [Exploring Generative Neural Temporal Point Process](https://mlsanity.com/paper/2208.01874/) (2022)
- [Deep Mixture Point Processes: Spatio-temporal Event Prediction with Rich Contextual Information](https://mlsanity.com/paper/1906.08952/) (2019)
- [Efficient Bayesian Inference of Sigmoidal Gaussian Cox Processes](https://mlsanity.com/paper/1808.00831/) (2018)
- [Approximate Bayes learning of stochastic differential equations](https://mlsanity.com/paper/1702.05390/) (2017)
- [Information Theoretic Meta Learning with Gaussian Processes](https://mlsanity.com/paper/2009.03228/) (2020)
- [An Empirical Study: Extensive Deep Temporal Point Process](https://mlsanity.com/paper/2110.09823/) (2021)
- [Practical Challenges in Differentially-Private Federated Survival Analysis of Medical Data](https://mlsanity.com/paper/2202.03758/) (2022)
- [Decoupled Marked Temporal Point Process using Neural Ordinary Differential Equations](https://mlsanity.com/paper/2406.06149/) (2024)
- [Federated Bayesian Neural Regression: A Scalable Global Federated Gaussian Process](https://mlsanity.com/paper/2206.06357/) (2022)
- [Efficient Bayesian Inference for a Gaussian Process Density Model](https://mlsanity.com/paper/1805.11494/) (2018)
- [Heterogeneous Multi-Task Gaussian Cox Processes](https://mlsanity.com/paper/2308.15364/) (2023)
- [FedSI: Federated Subnetwork Inference for Efficient Uncertainty Quantification](https://mlsanity.com/paper/2404.15657/) (2024)
- [Stabilizing and Improving Federated Learning with Non-IID Data and Client Dropout](https://mlsanity.com/paper/2303.06314/) (2023)
- [Bayesian Personalized Federated Learning with Shared and Personalized Uncertainty Representations](https://mlsanity.com/paper/2309.15499/) (2023)

## Built on by (most cited first, 3 of 3)

- [UFGraphFR: Graph Federation Recommendation System based on User Text description features](https://mlsanity.com/paper/2501.08044/) (2025)
- [Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval](https://mlsanity.com/paper/2604.15951/) (2026)
- [FedUAF: Uncertainty-Aware Fusion with Reliability-Guided Aggregation for Multimodal Federated Sentiment Analysis](https://mlsanity.com/paper/2603.13291/) (2026)

## Abstract (arXiv)

Temporal point processes (TPPs) are effective for modeling event occurrences over time, but they struggle with sparse and uncertain events in federated systems, where privacy is a major concern. To address this, we propose textitFedPP, a Federated neural nonparametric Point Process model. FedPP integrates neural embeddings into Sigmoidal Gaussian Cox Processes (SGCPs) on the client side, which is a flexible and expressive class of TPPs, allowing it to generate highly flexible intensity functions that capture client-specific event dynamics and uncertainties while efficiently summarizing historical records. For global aggregation, FedPP introduces a divergence-based mechanism that communicates the distributions of SGCPs' kernel hyperparameters between the server and clients, while keeping client-specific parameters local to ensure privacy and personalization. FedPP effectively captures event uncertainty and sparsity, and extensive experiments demonstrate its superior performance in federated settings, particularly with KL divergence and Wasserstein distance-based global aggregation.