Molecular Contrastive Learning with Chemical Element Knowledge Graph

Personal Knowledge/Learning Graph

Educational data mining and learning analytics have to date largely focused on specific research questions that provide insight into granular interactions. These insights have been abstracted to include the development of predictive models, intelligent tutors, and adaptive learning. While there are several domains where holistic or systems models have provided additional explanatory power, work...

9. Contrastive Knowledge

Contrastive Knowledge Surveyed

Suppose that Ann says, “Keith knows that the bank will be open tomorrow.” Her audience may well agree. Her knowledge ascription may seem true. But now suppose that Ben—in a different context—also says “Keith knows that the bank will be open tomorrow.” His audience may well disagree. His knowledge ascription may seem false. Indeed, a number of philosophers have claimed that people’s intuitions a...

Convolutional Neural Knowledge Graph Learning

Previous models for learning entity and relationship embeddings of knowledge graphs such as TransE, TransH, and TransR aim to explore new links based on learned representations. However, these models interpret relationships as simple translations on entity embeddings. In this paper, we try to learn more complex connections between entities and relationships. In particular, we use a Convolutiona...

On Contrastive Divergence Learning

Maximum-likelihood (ML) learning of Markov random fields is challenging because it requires estimates of averages that have an exponential number of terms. Markov chain Monte Carlo methods typically take a long time to converge on unbiased estimates, but Hinton (2002) showed that if the Markov chain is only run for a few steps, the learning can still work well and it approximately minimizes a d...