Geometry-enhanced molecular representation learning for property prediction

Text-Enhanced Representation Learning for Knowledge Graph

Learning the representations of a knowledge graph has attracted significant research interest in the field of intelligent Web. By regarding each relation as one translation from head entity to tail entity, translation-based methods including TransE, TransH and TransR are simple, effective and achieving the state-of-the-art performance. However, they still suffer the following issues: (i) low pe...

Multi-task Representation Learning for Demographic Prediction

Demographic attributes are important resources for market analysis, which are widely used to characterize different types of users. However, such signals are only available for a small fraction of users due to the difficulty in manual collection process by retailers. Most previous work on this problem explores different types of features and usually predicts different attributes independently. ...

Representation Learning for Resource Usage Prediction

Creating a model of a computer system that can be used for tasks such as predicting future resource usage and detecting anomalies is a challenging problem. Most current systems rely on heuristics and overly simplistic assumptions about the workloads and system statistics. These heuristics are typically a one-size-fits-all solution so as to be applicable in a wide range of applications and syste...

Selection of Molecular Descriptor Subsets for Property Prediction

Knowledge Representation in a Learning Environment for Euclidean Geometry

In the current constructivist approach to science and mathematics education computer systems play an important role. They provide unique opportunities for enriching the understanding of the subject: no other learning tool reaches their usability, versatility and power for representing concepts and processes, giving students direct access to exploration and manipulation. They are cognitive and m...