Avijit Ghosh
PhD Student
Education
- M.Tech. in Financial Engineering, Indian Institute of Technology, Kharagpur – India
- B.Tech. in Chemical Engineering, Indian Institute of Technology, Kharagpur – India
Biography
Avijit is a doctoral student at the Khoury College of Computer Sciences, currently advised by Christo Wilson and Alan Mislove. He studies fairness, transparency, and ethics in algorithms, and strives to find answers to questions about the societal impacts of modern data-driven platforms and technology’s role in addressing inequality.
Avijit currently looks at algorithmic interventions for debiasing machine learning algorithms, with a focus on ranking and recommendation models, with an aim to uncover and alleviate problems in existing debiasing interventions that work great in theory, but do not translate well in a real-life context. In the future, Avijit would like to continue in academic research.
Recent Publications
-
When Fair Ranking Meets Uncertain Inference
Citation: Avijit Ghosh, Ritam Dutt, and Christo Wilson. "When Fair Ranking Meets Uncertain Inference". In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021). Virtual Event, Canada, July, 2021. DOI: 10.1145/3506803 -
FairCanary: Rapid Continuous Explainable Fairness
Citation: Ghosh, Avijit, and Aalok Shanbhag. "FairCanary: Rapid Continuous Explainable Fairness." arXiv preprint arXiv:2106.07057 (2021) -
Building and Auditing Fair Algorithms: A Case Study in Candidate Screening
Citation: Christo Wilson, Avijit Ghosh, Shan Jiang, Alan Mislove, Lewis Baker, Janelle Szary, Kelly Trindel, and Frida Polli. "Building and Auditing Fair Algorithms: A Case Study in Candidate Screening." In Proceedings of the Conference on Fairness, Accountability, and Transparency (FAccT 2021). Virtual Event, Canada, March, 2021. DOI: 10.1145/3442188.3445928
