Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs

Rakshit Trivedi, Hanjun Dai, Yichen Wang, Le Song
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:3462-3471, 2017.

Abstract

The availability of large scale event data with time stamps has given rise to dynamically evolving knowledge graphs that contain temporal information for each edge. Reasoning over time in such dynamic knowledge graphs is not yet well understood. To this end, we present Know-Evolve, a novel deep evolutionary knowledge network that learns non-linearly evolving entity representations over time. The occurrence of a fact (edge) is modeled as a multivariate point process whose intensity function is modulated by the score for that fact computed based on the learned entity embeddings. We demonstrate significantly improved performance over various relational learning approaches on two large scale real-world datasets. Further, our method effectively predicts occurrence or recurrence time of a fact which is novel compared to prior reasoning approaches in multi-relational setting.

Cite this Paper

BibTeX
@InProceedings{pmlr-v70-trivedi17a, title = {Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs}, author = {Rakshit Trivedi and Hanjun Dai and Yichen Wang and Le Song}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {3462--3471}, year = {2017}, editor = {Precup, Doina and Teh, Yee Whye}, volume = {70}, series = {Proceedings of Machine Learning Research}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/trivedi17a/trivedi17a.pdf}, url = {https://proceedings.mlr.press/v70/trivedi17a.html}, abstract = {The availability of large scale event data with time stamps has given rise to dynamically evolving knowledge graphs that contain temporal information for each edge. Reasoning over time in such dynamic knowledge graphs is not yet well understood. To this end, we present Know-Evolve, a novel deep evolutionary knowledge network that learns non-linearly evolving entity representations over time. The occurrence of a fact (edge) is modeled as a multivariate point process whose intensity function is modulated by the score for that fact computed based on the learned entity embeddings. We demonstrate significantly improved performance over various relational learning approaches on two large scale real-world datasets. Further, our method effectively predicts occurrence or recurrence time of a fact which is novel compared to prior reasoning approaches in multi-relational setting.} }
Endnote
%0 Conference Paper %T Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs %A Rakshit Trivedi %A Hanjun Dai %A Yichen Wang %A Le Song %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-trivedi17a %I PMLR %P 3462--3471 %U https://proceedings.mlr.press/v70/trivedi17a.html %V 70 %X The availability of large scale event data with time stamps has given rise to dynamically evolving knowledge graphs that contain temporal information for each edge. Reasoning over time in such dynamic knowledge graphs is not yet well understood. To this end, we present Know-Evolve, a novel deep evolutionary knowledge network that learns non-linearly evolving entity representations over time. The occurrence of a fact (edge) is modeled as a multivariate point process whose intensity function is modulated by the score for that fact computed based on the learned entity embeddings. We demonstrate significantly improved performance over various relational learning approaches on two large scale real-world datasets. Further, our method effectively predicts occurrence or recurrence time of a fact which is novel compared to prior reasoning approaches in multi-relational setting.
APA
Trivedi, R., Dai, H., Wang, Y. & Song, L.. (2017). Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:3462-3471 Available from https://proceedings.mlr.press/v70/trivedi17a.html.

Related Material