In-Context Learning of Temporal Point Processes with Foundation Inference Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912930619981824 |
|---|---|
| author | Berghaus, David Seifner, Patrick Cvejoski, Kostadin Ojeda, César Sánchez, Ramsés J. |
| author_facet | Berghaus, David Seifner, Patrick Cvejoski, Kostadin Ojeda, César Sánchez, Ramsés J. |
| contents | Modeling event sequences of multiple event types with marked temporal point processes (MTPPs) provides a principled way to uncover governing dynamical rules and predict future events. Current neural network approaches to MTPP inference rely on training separate, specialized models for each target system. We pursue a radically different approach: drawing on amortized inference and in-context learning, we pretrain a deep neural network to infer, in-context, the conditional intensity functions of event histories from a context defined by sets of event sequences. Pretraining is performed on a large synthetic dataset of MTPPs sampled from a broad distribution of Hawkes processes. Once pretrained, our Foundation Inference Model for Point Processes (FIM-PP) can estimate MTPPs from real-world data without any additional training, or be rapidly finetuned to target systems. Experiments show that this amortized approach matches the performance of specialized models on next-event prediction across common benchmark datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24762 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | In-Context Learning of Temporal Point Processes with Foundation Inference Models Berghaus, David Seifner, Patrick Cvejoski, Kostadin Ojeda, César Sánchez, Ramsés J. Machine Learning Modeling event sequences of multiple event types with marked temporal point processes (MTPPs) provides a principled way to uncover governing dynamical rules and predict future events. Current neural network approaches to MTPP inference rely on training separate, specialized models for each target system. We pursue a radically different approach: drawing on amortized inference and in-context learning, we pretrain a deep neural network to infer, in-context, the conditional intensity functions of event histories from a context defined by sets of event sequences. Pretraining is performed on a large synthetic dataset of MTPPs sampled from a broad distribution of Hawkes processes. Once pretrained, our Foundation Inference Model for Point Processes (FIM-PP) can estimate MTPPs from real-world data without any additional training, or be rapidly finetuned to target systems. Experiments show that this amortized approach matches the performance of specialized models on next-event prediction across common benchmark datasets. |
| title | In-Context Learning of Temporal Point Processes with Foundation Inference Models |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.24762 |