Srikanta Bedathur — accepted AI-conference papers

2026

Kernelized Edge Attention: Addressing Semantic Attention Blurring in Temporal Graph Neural Networks

Govind Waghmare, Srini Rohan Gujulla Leel, Nikhil Tumbde, Sumedh B G, Sonia Gupta, Srikanta Bedathur

AAAI 2026technical

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 or architectural design, they often compute attention over entangled node and edge representations, failing to reflect th

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

A Zero-Shot Neuro-Symbolic Approach for Complex Knowledge Graph Question Answering

Prerna Agarwal, Srikanta Bedathur

EMNLP 2025

Existing low-resource Knowledge Graph Question Answering (KGQA) methods rely heavily on Large Language Models (LLMs) for semantic parsing of natural language question to its corresponding logical form (LF) such as SPARQL, S-Expression, etc. However, LLMs becomes bottleneck for practical applications

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

SymKGQA: Few-Shot Knowledge Graph Question Answering via Symbolic Program Generation and Execution

Prerna Agarwal, Nishant Kumar, Srikanta Bedathur

ACL 2024long

Semantic Parsing of natural language questions into their executable logical form (LF) has shown state-of-the-art (SOTA) performance for Knowledge Graph Question Answering (KGQA). However, these methods are not applicable for real-world applications, due to lack of KG-specific training data. Recent…

Cited by 2 Source ↗PDF ↗Scholar ↗

2023

DetAIL: A Tool to Automatically Detect and Analyze Drift in Language

Nishtha Madaan, Adithya Manjunatha, Hrithik Nambiar, Aviral Goel, Harivansh Kumar, Diptikalyan Saha +1

AAAI 2023technical

Machine learning and deep learning-based decision making has become part of today's software. The goal of this work is to ensure that machine learning and deep learning-based systems are as trusted as traditional software. Traditional software is made dependable by following rigorous practice like s…

Cited by 6 Source ↗PDF ↗Scholar ↗

2022

Learning Temporal Point Processes for Efficient Retrieval of Continuous Time Event Sequences

Vinayak Gupta, Srikanta Bedathur, Abir De

AAAI 2022technical

Recent developments in predictive modeling using marked temporal point processes (MTPPs) have enabled an accurate characterization of several real-world applications involving continuous-time event sequences (CTESs). However, the retrieval problem of such sequences remains largely unaddressed in lit…

Cited by 16 Source ↗PDF ↗code ↗Scholar ↗

2022

TIGGER: Scalable Generative Modelling for Temporal Interaction Graphs

Shubham Gupta, Sahil Manchanda, Srikanta Bedathur, Sayan Ranu

AAAI 2022technical

There has been a recent surge in learning generative models for graphs. While impressive progress has been made on static graphs, work on generative modeling of temporal graphs is at a nascent stage with significant scope for improvement. First, existing generative models do not scale with either th…

Cited by 23 Source ↗PDF ↗code ↗Scholar ↗

2021

Learning Temporal Point Processes with Intermittent Observations

Vinayak Gupta, Srikanta Bedathur, Sourangshu Bhattacharya, Abir De

AISTATS 2021poster

Marked temporal point processes (MTPP) have emerged as a powerful framework to model the underlying generative mechanism of asynchronous events localized in continuous time. Most existing models and inference methods in MTPP framework consider only the complete observation scenario i.e. the event se…

Cited by 28 Source ↗PDF ↗code ↗Scholar ↗