In conjunction with the IEEE International Conference on Big Data (IEEE BigData 2014) on October 27, 2014, Washington DC, USA
Big data are encountered in various areas, including Internet search, social networks, finance, business sectors, meteorology, genomics, complex physics simulations, biological and environmental research. Machine learning as an important tool of big data analytics is playing more and more important roles in the big data era. However, the characteristics of large volume, high velocity, variety and veracity bring challenges to current machine learning techniques. It is therefore desirable to discuss
(1) how to scale up existing machine learning techniques for modeling and analyzing big data from various domains;
(2) how to design new machine learning algorithms for various parallel/distributed machine learning platforms (such as Hadoop, GraphLab, Spark, etc.); and
(3) how to design universal machine learning interfaces for GPUs or cloud computing architectures, and so on.
Topics of Interest
(1) how to scale up existing machine learning techniques for modeling and analyzing big data from various domains;
(2) how to design new machine learning algorithms for various parallel/distributed machine learning platforms (such as Hadoop, GraphLab, Spark, etc.); and
(3) how to design universal machine learning interfaces for GPUs or cloud computing architectures, and so on.
Topics of Interest
- Distributed data analytics architectures
- Data separation and integration techniques
- Machine learning algorithms for GPUs
- Machine learning algorithms for clouds
- Machine learning algorithms for clusters
- Theory and algorithms of data reduction techniques for big data
- Online/incremental/stochastic learning algorithms
- Random projection
- Hashing techniques
- Data sampling algorithms
- Theory and algorithms of large-scale matrix approximation
- Bound analysis of matrix approximation algorithms
- Distributed matrix factorization
- Distributed multiway array analysis
- Online dictionary learning
- Distributed topic modeling algorithms
- Heterogeneous learning on big multimodal data
- Multiview learning
- Multitask learning
- Transfer learning
- Semi-supervised learning
- Active learning
- Temporal analysis and spatial analysis in big data
- Real-time analysis for data stream
- Trend prediction in financial data
- Topic detection in instant message systems
- Real time modeling of events in dynamic networks
- Spatial modeling on maps
- Scalable machine learning in large graphs
- Communities discovery and analysis in social networks
- Link prediction in networks
- Anomaly detection in social networks
- Fusion of information from multiple blogs, rating systems, and social networks
- Integration of text, videos, images, sounds in social networks
- Recommender systems
- Novel applications of scalable machine learning in big data
- Decision making with big data
- Counterfactual reasoning with big data
- Medical/health informatics big data analysis
- Security big data analysis
- Astronomy big data analysis
- Biological big data analysis
- Urban/smart city big data analysis
- Education big data analysis