Deep Neural Networks have shown tremendous success in the area of object recognition, image classification and natural language processing. However, designing optimal Neural Network architectures that can learn and output arbitrary graphs is an ongoing research problem. The objective of this talk is to summarise and discuss the latest advances in methods to Learn Representations of Graph Data. We start by identifying commonly used types of graph data and review basics of graph theory. This is followed by a discussion of the relationships between graph kernel methods and neural networks. Next we identify the major approaches used for learning representations of graph data namely: Kernel approaches, Convolutional approaches, Graph neural networks approaches, Graph embedding approaches and Probabilistic approaches. A variety of methods under each of the approaches are discussed and the talk is concluded with a brief discussion of the future of learning representation of graph data.
Mital is wrapping her Doctoral Research studies at UCL in Machine Learning. She has an Msc in Machine Learning, MRes in Financial Computing and an MSc in Financial Engineering. She is also passionate about supporting BAME women into STEM careers. Her research is focused on developing statistical models for learning from different types of data. Outside of work she enjoys nature, creative writing and spending time with family.
Weeknotes for your personal development