activity
20242026
collaborators

5 papers

cs.CR2026

Bayesian Membership Privacy for Graph Neural Networks

Sinan Yıldırım, Megha Khosla

Existing privacy analyses for Graph Neural Networks (GNNs) largely inherit assumptions from non-graph settings, overlooking structural correlations and stochastic training-graph sa…

cs.LG2026

Impact of Graph Structure on Membership-Inference Risk for Graph Neural Networks

Megha Khosla

Graph neural networks (GNNs) are widely used for tasks such as node classification and link prediction, but their use in sensitive settings raises concerns about training-data leak…

cs.SI2026

Population-Scale Network Embeddings Expose Educational Divides in Network Structure Related to Right-Wing Populist Voting

Malte Lüken, Javier Garcia-Bernardo, Sreeparna Deb +2

Administrative registry data can be used to construct population-scale networks whose ties reflect shared social contexts between persons. With machine learning, such networks can…

cs.LG2025

Draw a Portrait of Your Graph Data: An Instance-Level Profiling Framework for Graph-Structured Data

Tianqi Zhao, Russa Biswas, Megha Khosla

Graph machine learning models often achieve similar overall performance yet behave differently at the node level, failing on different subsets of nodes with varying reliability. St…

cs.LG2024

GNN-MultiFix: Addressing the pitfalls for GNNs for multi-label node classification

Tianqi Zhao, Megha Khosla

Graph neural networks (GNNs) have emerged as powerful models for learning representations of graph data showing state of the art results in various tasks. Nevertheless, the superio…