IIIT-Delhi Institutional Repository

Browsing Computer Science and Engineering by Author "Prasad, Ranjitha (Advisor)"

Browsing Computer Science and Engineering by Author "Prasad, Ranjitha (Advisor)"

Sort by: Order: Results:

  • DAG-LIME : causal interpretability using directed acyclic graphs 
    Verma, Khushali; Prasad, Ranjitha (Advisor) (IIIT-Delhi, 2022-05)
    Widely adapted locally interpretable methods such as LIME [20] and SHAP [12] fail to capture the underlying causal relationships between the variables. They merely capture the linear and non-linear associations. These ...
  • Joint graph learning and prediction 
    Akhtar, Mohammad Hamzah; Sheoran, Shikhar; Prasad, Ranjitha (Advisor) (IIIT-Delhi, 2021-12)
    Estimating the structure of directed acyclic graphs (DAGs, also known as Bayesian networks) is a challenging problem since the search space of DAGs is combinatorial and scales super exponentially with the number of nodes. ...
  • Personalized federated self supervised multitask learning 
    Rastogi, Divyansh; Prasad, Ranjitha (Advisor) (IIIT-Delhi, 2022-12)
    Federated learning has been a popular research subject in allowing diverse people and businesses to collaborate on machine learning model training while maintaining privacy. Additionally, in today’s world there is an ...
  • Post-hoc explainable methods: uncertainty in counterfactual explanations 
    Reddy, Mortala Gautam; Prasad, Ranjitha (Advisor) (IIIT-Delhi, 2023-11-29)
    With the introduction of the EU’s GDPR in 2017, lawmakers have emphasized the importance of algorithmic decisions being explainable to people affected by those decisions. This has led to a major focus being put on Explainable ...
  • Temporal causal effect variational autoencoder 
    Aggarwal, Soumya; Gandhi, Vansh; Prasad, Ranjitha (Advisor) (IIIT-Delhi, 2023-12-12)
    This work is a review on causal inference with a focus on predicting temporal Individual Treatment Effects (ITEs). Various approaches were investigated, and the Causal Effect Variational Autoencoder (CEVAE) was selected ...

Search Repository


Advanced Search

Browse

My Account