Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs
Authors:
- Rakshit TrivediRTRakshit Trivedi
- Hanjun DaiHDHanjun Dai
- Yichen WangYWYichen Wang
- Le SongLSLe Song
Preprint
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.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Leveraging temporal autocorrelation of historical data for improving accuracy in network regressionStatistical Analysis and Data Mining: An ASA Data Science Journal, 2017
- Encoding Temporal Information for Time-Aware Link Prediction2016
- Learning Entity and Relation Embeddings for Knowledge Graph CompletionProceedings of the AAAI Conference on Artificial Intelligence, 2015
- Observed versus latent features for knowledge base and text inference2015
- Knowledge Graph Embedding by Translating on HyperplanesProceedings of the AAAI Conference on Artificial Intelligence, 2014
- A self-correcting point processStochastic Processes and their Applications, 1979