activity
20232025
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2025

Learning from Heterophilic Graphs: A Spectral Theory Perspective on the Impact of Self-Loops and Parallel Edges

Kushal Bose, Swagatam Das

Graph heterophily poses a formidable challenge to the performance of Message-passing Graph Neural Networks (MP-GNNs). The familiar low-pass filters like Graph Convolutional Network…

cs.LG2025

Asynchronous Message Passing for Addressing Oversquashing in Graph Neural Networks

Kushal Bose, Swagatam Das

Graph Neural Networks (GNNs) suffer from oversquashing, where structural bottlenecks limit message propagation between distant nodes, hindering tasks that require long-range intera…

cs.LG2025

Transformers Are Universally Consistent

Sagar Ghosh, Kushal Bose, Swagatam Das

Despite their central role in the success of foundational models and large-scale language modeling, the theoretical foundations governing the operation of Transformers remain only…

cs.LG2025

Topology-Driven Clustering: Enhancing Performance with Betti Number Filtration

Arghya Pratihar, Kushal Bose, Swagatam Das

Clustering aims at partitioning data points into groups of similar objects without knowing about the class labels. However, clustering datasets with complex geometric structures, s…

cs.LG2023

HyPE-GT: where Graph Transformers meet Hyperbolic Positional Encodings

Kushal Bose, Swagatam Das

Graph Transformers (GTs) facilitate the comprehension of complex relationships on graph-structured data by leveraging self-attention of the possible pairs of nodes. The structural…