Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs
It addresses the problem of temporal reasoning in dynamic knowledge graphs for applications like event prediction, offering a novel approach compared to prior methods.
The paper tackles reasoning over time in dynamic knowledge graphs by introducing Know-Evolve, a deep evolutionary knowledge network that models facts as a multivariate point process, resulting in significantly improved performance on two large-scale real-world datasets and novel predictions for fact occurrence or recurrence times.
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.