Wasing the always of wanting of knowing.
The eternal desire of a hungry soul is knowledge.
– Mistborn Series, Brandon Sanderson
My goal is to use theoretical and empirical insights to develop a principled understanding of small-scale representations of graphs and machine learning (ML)models so that they are reliable when deployed in the real-world. In particular, my focus is on Node Embeddings which distill high-dimensional feature and neighbourhood information onto low-dimensional spaces. Currently, I am thinking about the following problems:
Node embedding algorithms are typically designed for ML tasks such as node classification and link prediction. How applicable are these embeddings for traditional graph mining tasks such as summarization and query answering? How do they compare against other types of small-scale representations?
Node embeddings are smaller abstractions of graphs which model users and relationships in the context of social networks. Do such models exacerbate or reduce the harmful biases of real-world applications? How do we account for bias in the data so that it does not propagate into the embedding?
In the past, I worked on a related theme in the context of machine teaching. How can we construct useful training examples to simultaneously train stochastic gradient descent learners when we have incomplete or noisy information about them?
On the application side, I am excited about computational social science wherein I am interested in human behaviour on online social networks. My past research has explored how platforms facilitate trustworthiness amongst users through incentives and gamification. I have also studied the role of digital signalling on the actions, social capital, and social status of users online.