Zhang, Q;
Lipani, A;
Yilmaz, E;
(2021)
Learning Neural Point Processes with Latent Graphs.
In:
WWW '21: Proceedings of the Web Conference 2021.
(pp. pp. 1495-1505).
ACM
Preview |
Text
2021_WWW_Learning_Neural_Point_Processes_with_Latent_Graphs.pdf - Accepted Version Download (2MB) | Preview |
Abstract
Neural point processes (NPPs) employ neural networks to capture complicated dynamics of asynchronous event sequences. Existing NPPs feed all history events into neural networks, assuming that all event types contribute to the prediction of the target type. How- ever, this assumption can be problematic because in reality some event types do not contribute to the predictions of another type. To correct this defect, we learn to omit those types of events that do not contribute to the prediction of one target type during the formulation of NPPs. Towards this end, we simultaneously consider the tasks of (1) finding event types that contribute to predictions of the target types and (2) learning a NPP model from event se- quences. For the former, we formulate a latent graph, with event types being vertices and non-zero contributing relationships being directed edges; then we propose a probabilistic graph generator, from which we sample a latent graph. For the latter, the sampled graph can be readily used as a plug-in to modify an existing NPP model. Because these two tasks are nested, we propose to optimize the model parameters through bilevel programming, and develop an efficient solution based on truncated gradient back-propagation. Experimental results on both synthetic and real-world datasets show the improved performance against state-of-the-art baselines. This work removes disturbance of non-contributing event types with the aid of a validation procedure, similar to the practice to mitigate overfitting used when training machine learning models.
| Type: | Proceedings paper |
|---|---|
| Title: | Learning Neural Point Processes with Latent Graphs |
| Event: | World Wide Web Conference |
| ISBN-13: | 978-1-4503-8312-7 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1145/3442381.3450135 |
| Publisher version: | https://doi.org/10.1145/3442381.3450135 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Civil, Environ and Geomatic Eng UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10122006 |
Archive Staff Only
 |
View Item |
