Search Results for author: Sankarshan Damle

Found 6 papers, 2 papers with code

Exploring Continual Fine-Tuning for Enhancing Language Ability in Large Language Model

no code implementations21 Oct 2024 Divyanshu Aggarwal, Sankarshan Damle, Navin Goyal, Satya Lokam, Sunayana Sitaram

A common challenge towards the adaptability of Large Language Models (LLMs) is their ability to learn new languages over time without hampering the model's performance on languages in which the model is already proficient (usually English).

Language Modelling Large Language Model

Designing Redistribution Mechanisms for Reducing Transaction Fees in Blockchains

no code implementations24 Jan 2024 Sankarshan Damle, Manisha Padala, Sujit Gujar

As these blockchains are a public resource, it may be preferable to reduce these transaction fees.

Combinatorial Civic Crowdfunding with Budgeted Agents: Welfare Optimality at Equilibrium and Optimal Deviation

no code implementations25 Nov 2022 Sankarshan Damle, Manisha Padala, Sujit Gujar

Further, funding the optimal social welfare subset of projects is desirable when every available project cannot be funded due to budget restrictions.

Differentially Private Federated Combinatorial Bandits with Constraints

no code implementations27 Jun 2022 Sambhav Solanki, Samhita Kanaparthy, Sankarshan Damle, Sujit Gujar

There is a rapid increase in the cooperative learning paradigm in online learning settings, i. e., federated learning (FL).

Federated Learning Privacy Preserving

F3: Fair and Federated Face Attribute Classification with Heterogeneous Data

1 code implementation6 Sep 2021 Samhita Kanaparthy, Manisha Padala, Sankarshan Damle, Ravi Kiran Sarvadevabhatla, Sujit Gujar

F3 adopts multiple heuristics to improve fairness across different demographic groups without requiring data homogeneity assumption.

Attribute Classification +2

Federated Learning Meets Fairness and Differential Privacy

1 code implementation23 Aug 2021 Manisha Padala, Sankarshan Damle, Sujit Gujar

Deep learning's unprecedented success raises several ethical concerns ranging from biased predictions to data privacy.

Fairness Federated Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.