The existing literature on knowledge graph completion mostly focuses on the link prediction task.
The most successful prior approaches for modeling such time series are based on recurrent neural networks that learn to impute unobserved values and then treat the imputed values as observed.
We present MMKG, a collection of three knowledge graphs that contain both numerical features and (links to) images for all entities as well as entity alignments between pairs of KGs.
Extracting actionable insight from Electronic Health Records (EHRs) poses several challenges for traditional machine learning approaches.
Many real-world domains can be expressed as graphs and, more generally, as multi-relational knowledge graphs.
We present our ongoing work on understanding the limitations of graph convolutional networks (GCNs) as well as our work on generalizations of graph convolutions for representing more complex node attribute dependencies.
This is exploited in sentiment analysis where machine learning models are used to predict the review score from the text of the review.
We present KBLRN, a framework for end-to-end learning of knowledge base representations from latent, relational, and numerical features.
We present Net2Vec, a flexible high-performance platform that allows the execution of deep learning algorithms in the communication network.
This paper tackles the problem of endogenous link prediction for Knowledge Base completion.
We consider the problem of embedding entities and relationships of multi-relational data in low-dimensional vector spaces.
Ranked #5 on Link Prediction on FB122
We consider the problem of embedding entities and relations of knowledge bases in low-dimensional vector spaces.