Dr. Charu Sharma gave a talk on machine learning for graphs and its applications at the department of Computer Science and Engineering, IIT Jammu on 16 November.
Here is the summary of the talk: Graph embedding methods have gained attention in a wide variety of tasks including node classification, link prediction, etc. In machine learning, the task of producing graph embeddings entails capturing local and global graph statistics and encoding them as vectors that best preserve these statistics in a computationally efficient manner. Additionally, The recent proliferation of knowledge graphs (KGs) coupled with incomplete or partial information, in the form of missing relations (links) between entities, has fueled a lot of research on knowledge base completion. KGs are widely used in various domains from question-answering to information retrieval to relation prediction. This talk covered the introduction to graphs and KGs in ML/DL, challenges to work with graphs, applications in different domains and learning representations. Graph embeddings include different representations, learning methods and structural information in order to perform various tasks.