5 papers
Kernelized Edge Attention: Addressing Semantic Attention Blurring in Temporal Graph Neural Networks
Govind Waghmare, Srini Rohan Gujulla Leel, Nikhil Tumbde +3
Temporal Graph Neural Networks (TGNNs) aim to capture the evolving structure and timing of interactions in dynamic graphs. Although many models incorporate time through encodings o…
Flow Matters: Directional and Expressive GNNs for Heterophilic Graphs
Arman Gupta, Govind Waghmare, Gaurav Oberoi +1
In heterophilic graphs, where neighboring nodes often belong to different classes, conventional Graph Neural Networks (GNNs) struggle due to their reliance on local homophilous nei…
Efficient Graph Understanding with LLMs via Structured Context Injection
Govind Waghmare, Sumedh BG, Sonia Gupta +1
Large Language Models (LLMs) have shown strong capabilities in solving problems across domains, including graph-related tasks traditionally addressed by symbolic or algorithmic met…
A Scalable Approach to Covariate and Concept Drift Management via Adaptive Data Segmentation
Vennela Yarabolu, Govind Waghmare, Sonia Gupta +1
In many real-world applications, continuous machine learning (ML) systems are crucial but prone to data drift, a phenomenon where discrepancies between historical training data and…
Modeling Inter-Dependence Between Time and Mark in Multivariate Temporal Point Processes
Govind Waghmare, Ankur Debnath, Siddhartha Asthana +1
Temporal Point Processes (TPP) are probabilistic generative frameworks. They model discrete event sequences localized in continuous time. Generally, real-life events reveal descrip…