My goal is to use theoretical and empirical insights to develop a principled understanding of machine learning (ML) models so that they are reliable when deployed in the real-world. More concretely, I am thinking about the following problems:
Graph embeddings distill high-dimensional feature and neighbourhood information onto low-dimensional spaces so that they can be used to perform ML tasks such as node classification and link prediction. I seek to formally explore the relationship between robustness and traditional notions of performance (e.g. accuracy), especially in the presence of random as well as structural perturbations to the input graph, and uncertainty in the form of noisy or unavailable data.
When we use graph embeddings for downstream tasks, it is imperative to ensure that they are systemically sound and safe to use. I am working on building models that are provably guaranteed to be robust and fair by design.
- Merchant A., Shah D., Bhatia G. S., Ghosh A., Kumaraguru P. (2019). Signals Matter : Understanding Popularity and Impact of Users on Stack Overflow. In Proceedings of the 30th ACM Conference on World Wide Web. WebConf (San Francisco, USA, May 13-17 2019).
- Yeo T., Parameswaran K., Singla A., Merchant A., Faucon P., Asselborn T., Dillenbourg P., Cevher V. (2019). Iterative Classroom Teaching. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence. AAAI (Hawaii, USA, January 27 - February 1, 2019).
- Tschiatschek S., Singla A., Gomez-Rodriguez M., Merchant A., Krause A. (2018). Detecting Fake News in Social Networks via Crowdsourcing. In Proceedings of the 29th ACM Conference on World Wide Web. WebConf (Lyon, France, April 23-27, 2018).
- Merchant A., Singh N. (2017). Hybrid Trust-Aware Model for Personalized Top-N Recom- mendation. In Proceedings of the 4th ACM Conference of Data Science. CODS (Chennai, India, March 8-11, 2017). Best Poster Award.
- Merchant A., Jha T., Singh N. (2016). The Use of Trust in Social Machines. In Proceedings of the 4th International Workshop on the Theory and Practice of Social Machines at World Wide Web Conference, WWW. (Montreal, Canada, April 11-15, 2016).