Srikanta J. Bedathur — accepted AI-conference papers

2025

Differentiable Adversarial Attacks for Marked Temporal Point Processes

Pritish Chakraborty, Vinayak Gupta, Rahul R, Srikanta J. Bedathur, Abir De

AAAI 2025technical

Marked temporal point processes (MTPPs) have been shown to be extremely effective in modeling continuous time event sequences (CTESs). In this work, we present adversarial attacks designed specifically for MTPP models. A key criterion for a good adversarial attack is its imperceptibility. For object…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

GRAFENNE: Learning on Graphs with Heterogeneous and Dynamic Feature Sets

Shubham Gupta, Sahil Manchanda, Sayan Ranu, Srikanta J. Bedathur

ICML 2023poster

Graph neural networks (GNNs), in general, are built on the assumption of a static set of features characterizing each node in a graph. This assumption is often violated in practice. Existing methods partly address this issue through feature imputation. However, these techniques (i) assume uniformity…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗