1 citations · 1 across the 7 of their papers we have counts for
8 papers
SGS-GNN: A Supervised Graph Sparsification method for Graph Neural Networks
Siddhartha Shankar Das, Naheed Anjum Arafat, Muftiqur Rahman +3
We propose SGS-GNN, a novel supervised graph sparsifier that learns the sampling probability distribution of edges and samples sparse subgraphs of a user-specified size to reduce t…
Logical Consistency of Large Language Models in Fact-checking
Bishwamittra Ghosh, Sarah Hasan, Naheed Anjum Arafat +1
In recent years, large language models (LLMs) have demonstrated significant success in performing varied natural language tasks such as language translation, question-answering, su…
When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learning
Naheed Anjum Arafat, Debabrota Basu, Yulia Gel +1
Capitalizing on the intuitive premise that shape characteristics are more robust to perturbations, we bridge adversarial graph learning with the emerging tools from computational t…
Finite Volume Features, Global Geometry Representations, and Residual Training for Deep Learning-based CFD Simulation
Loh Sher En Jessica, Naheed Anjum Arafat, Wei Xian Lim +2
Computational fluid dynamics (CFD) simulation is an irreplaceable modelling step in many engineering designs, but it is often computationally expensive. Some graph neural network (…
Neighborhood-based Hypergraph Core Decomposition
Naheed Anjum Arafat, Arijit Khan, Arpit Kumar Rai +1
We propose neighborhood-based core decomposition: a novel way of decomposing hypergraphs into hierarchical neighborhood-cohesive subhypergraphs. Alternative approaches to decomposi…
-net Induced Lazy Witness Complexes on Graphs
Naheed Anjum Arafat, Debabrota Basu, Stéphane Bressan
Computation of persistent homology of simplicial representations such as the Rips and the Cěch complexes do not efficiently scale to large point clouds. It is, therefore, meaningfu…
Construction and Random Generation of Hypergraphs with Prescribed Degree and Dimension Sequences
Naheed Anjum Arafat, Debabrota Basu, Laurent Decreusefond +1
We propose algorithms for construction and random generation of hypergraphs without loops and with prescribed degree and dimension sequences. The objective is to provide a starting…
Topological Data Analysis with -net Induced Lazy Witness Complex
Naheed Anjum Arafat, Debabrota Basu, Stéphane Bressan
Topological data analysis computes and analyses topological features of the point clouds by constructing and studying a simplicial representation of the underlying topological stru…