Home
About Us
Projects
Researchers
All Careers
Internships
Publications
Locations
External Research Office

Pallika Kanani

Oracle Labs
Researchers

Pallika Kanani

Research Director

Pallika Kanani

Personal page: https://pallika.github.io/

Pallika Kanani leads the research in Privacy Preserving Machine Learning within the Machine Learning Research Group at Oracle Labs. Her broad research interests are Federated Learning, Fairness and Privacy in Machine Learning, Natural Language Processing, and AI Governance. During her ten years at Oracle, she has worked closely with several different product groups on real world applications of Machine Learning. These application domains include Sales, Marketing, HR, Retail, Finance, Healthcare, and Social Media Analytics. Many of these collaborations have resulted in new product features, patents and publications. Pallika completed her PhD from UMass, Amherst, her M.S. in Computer Science from New York University, and her Bachelor of Engineering from University of Mumbai in India.

Publications

Conference Publication

Pallika Kanani

Research Director

Publications

Subject Level Differential Privacy with Hierarchical Gradient Averaging

Subject Membership Inference Attacks in Federated Learning

Subject Granular Differential Privacy in Federated Learning

Private Federated Learning with Domain Adaptation

Subject Membership Inference Attacks in Federated Learning.

Subject Granular Differential Privacy in Federated Learning.

Private Cross-Silo Federated Learning for Extracting Vaccine Adverse Event Mentions

Private Cross-Silo Federated Learning for Extracting Vaccine Adverse Event Mentions

PRIVATE CROSS-SILO FEDERATED LEARNING FOR EXTRACTING VACCINE ADVERSE EVENT MENTIONS

Private Cross-Silo Federated Learning for Extracting Vaccine Adverse Event Mentions.

Private Cross-Silo Federated Learning for Extracting Vaccine Adverse Event Mentions.

Private Federated Learning with Domain Adaptation

“Using Bayes Factors to Control for Fairness A Case Study on Learning to Rank”

Private Federated Learning with Domain Adaptation.

Minimally Constrained Multilingual Word Embeddings via Artificial Code Switching

Minimally Constrained Multilingual Word Embeddings via Artificial Code Switching

Attribute Extraction from Noisy Text Using Character-based Sequence Tagging Models

Resource-bounded Information Acquisition and Learning

Selecting Actions for Resource-bounded Information Extraction using Reinforcement Learning

Learning to Select Actions for Resource-bounded Information Extraction

How good is a span of terms? Exploiting proximity to improve web retrieval

Resource-bounded Information Extraction: Acquiring Missing Feature Values On Demand

Towards Theoretical Bounds for Resource-bounded Information Gathering for Correlation Clustering

Prediction-time Active Feature-value Acquisition for Cost-Effective Customer Targeting

Efficient Strategies for Improving Partitioning-Based Author Coreference by Incorporating Web Pages as Graph Nodes

Resource-bounded Information Gathering for Correlation Clustering

Improving Author Coreference by Resource-bounded Information Gathering from the Web

Author Disambiguation using Error-driven Machine Learning with a Ranking Loss Function

The effects of sampling frequency on developmental trajectories

A microgenetic analysis of the trajectory of motor development

Continuity and discontinuity in motor skill acquisition

Resources For

Partners

Emerging Technology

What’s New

Contact Us