Prasenjit Mitra

About

Prasenjit Mitra is a Professor of Information Sciences & Technology at Pennsylvania State University and a Graduate Faculty member in Social Data Analytics. He is also a C-SoDA Faculty Affiliate. His educational background includes a Ph.D. in Electrical Engineering from Stanford University, obtained in 2004, a Master of Science in Computer Science from The University of Texas at Austin in 1994, and a B.Tech. (Honours) in Computer Science and Engineering from the Indian Institute of Technology, Kharagpur, in 1993. His research focuses on social data analytics, leveraging his expertise in electrical engineering and computer science to advance understanding in this interdisciplinary field. He is actively involved in the academic community through his faculty affiliation and contributions to the Social Data Analytics program at Penn State.

Research topics

• Sociology
• Computer Science
• Political Science
• Geography
• Law
• Business
• Socioeconomics
• Data science

Selected publications

• Transferring Robustness for Graph Neural Network Against Poisoning Attacks

  2020-01-20 · 190 citations

  preprintOpen access

  Graph neural networks (GNNs) are widely used in many applications. However, their robustness against adversarial attacks is criticized. Prior studies show that using unnoticeable modifications on graph topology or nodal features can significantly reduce the performances of GNNs. It is very challenging to design robust graph neural networks against poisoning attack and several efforts have been taken. Existing work aims at reducing the negative impact from adversarial edges only with the poisoned…

  PublisherOA PDFDOI

• Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values

  Proceedings of the AAAI Conference on Artificial Intelligence · 2020-04-03 · 120 citations

  articleOpen access

  Multivariate time series (MTS) forecasting is widely used in various domains, such as meteorology and traffic. Due to limitations on data collection, transmission, and storage, real-world MTS data usually contains missing values, making it infeasible to apply existing MTS forecasting models such as linear regression and recurrent neural networks. Though many efforts have been devoted to this problem, most of them solely rely on local dependencies for imputing missing values, which ignores global…

  PublisherOA PDFDOI

• Unlearning Backdoor Attacks in Federated Learning

  2024-09-30 · 19 citations

  article

  Federated learning systems are constantly under the looming threat of backdoor attacks. Despite significant progress in mitigating such attacks, the challenge of effectively removing a potential attacker’s influence from the trained global model remains unresolved. In this paper, we present a novel federated unlearning method that is suitable for backdoor removal. By leveraging historical updates subtraction and knowledge distillation, our approach can maintain the models’s performance while com…

  PublisherDOI

• Crisis Informatics: Human-Centered Research on Tech & Crises

  HAL (Le Centre pour la Communication Scientifique Directe) · 2020 · 14 citations

• SiReRAG: Indexing Similar and Related Information for Multihop Reasoning

  Qeios · 2024-12-18 · 6 citations

  preprintOpen access

  Indexing is an important step towards strong performance in retrieval-augmented generation (RAG) systems. However, existing methods organize data based on either semantic similarity (similarity) or related information (relatedness), but do not cover both perspectives comprehensively. Our analysis reveals that modeling only one perspective results in insufficient knowledge synthesis, leading to suboptimal performance on complex tasks requiring multihop reasoning. In this paper, we propose SiReRAG…

  PublisherOA PDFDOI

Recent grants

• CAREER: An Integrated Framework for Extracting and Utilizing Information from Tables and Figures in Digital Libraries

  NSF · $450k · 2009–2014

Frequent coauthors

• C. Lee Giles

  108 shared

• Cornelia Caragea

  26 shared

• Prakhar Biyani

  Yahoo (United States)

  26 shared

• Greta E. Greer

  American Cancer Society

  23 shared

• Kenneth M. Portier

  University of Florida

  23 shared

• Lior Rokach

  Ben-Gurion University of the Negev

  22 shared

• Kang Zhao

  University of Iowa

  22 shared

• Shreya Ghosh

  21 shared

Labs

• Social Data AnalyticsPI

Education

• Ph.D.

  Stanford University

  2004

Similar researchers at Pennsylvania State University

• Duane Alwinh-64
• Stephanie Lanzah-56
• Vasant Honavarh-53