IEEE ICDM Workshop on Deep Learning for Spatiotemporal Data, Algorithms, and Systems
The complementary strengths and challenges between spatiotemporal data computing and deep learning in recent years suggest urgent needs to bring together the experts in these two domains in prestigious venues, which is still missing until now. This workshop will provide a premium platform for both research and industry to exchange ideas on opportunities, challenges, and cutting-edge techniques of deep learning in spatiotemporal data, algorithms, and systems. Full research papers and short position papers will be accepted under the topics include, but not limited to, the following two broad categories:
Novel Deep Learning Techniques for Spatial and Spatio-Temporal Data:
Convolutional, recurrent, and deep neural network techniques.
Representation learning and embedding based on deep learning
Scalable deep learning algorithms for large data.
Interpretable deep learning for spatial-temporal data.
Learning representation on heterogeneous networks, knowledge graphs
Deep generative models, adversarial machine learning
Deep reinforcement learning
Theory of deep learning for spatio-temporal data
Novel Deep Learning Applications for Spatial and Spatio-Temporal Data:
Remote sensing and land cover change detection/classification
Trajectory/mobility data mining and prediction
Location-based social network data analytics, event prediction and forecasting
Smart cities and ride-sharing (e.g., taxi demand forecasting)
Other applications of deep learning