Kushal Bose (He/Him)

Kushal Bose (He/Him)

Researcher of GNN and Hyperbolic spaces

Publication

  1. Kushal Bose and Swagatam Das. “Learning from Heterophilic Graphs: A Spectral Theory Perspective on the Impact of Self-Loops and Parallel Edges”. Just Accepted in the IEEE Transactions on Artificial Intelligence, 2026. (IEEE TAI) [arxiv]

  2. Indronil Ojha, Kushal Bose, and Swagatam Das. “FairSplit: Mitigating Bias in Graph Neural Networks through Sensitivity-based Edge Partitioning”. In the ACM Conference on Information and Knowledge Management, 2025 (ACM CIKM). [paper]

  3. Kushal Bose, Saptarshi Banerjee, and Swagatam Das. “Can Graph Neural Networks Tackle Heterophily? Yes, With a Label-Guided Graph Rewiring Approach!”. In IEEE Transactions on Neural Networks and Learning Systems, 2025 (IEEE TNNLS). [paper]

  4. Kushal Bose and Swagatam Das. “Can graph neural networks go deeper without over-smoothing? Yes, with a randomized path exploration!”. In IEEE Transactions on Emerging Topics and Computational Intelligence, 2025 (IEEE TETCI). [paper]

  5. Indronil Ojha, Kushal Bose, and Swagatam Das. “Affinity-based Homophily: Can we measure homophily of a graph without using node labels?”. In International Conference on Learning Representations, Tiny Papers (Invited to present), 2024 (ICLR). [paper]

  6. Kushal Bose and Swagatam Das. “HyPE-GT: where Graph Transformers meet Hyperbolic Positional Encodings”, (Under Revision). [arxiv]

  7. Kushal Bose and Swagatam Das. “Asynchronous Message Passing for Addressing Oversquashing in Graph Neural Networks”, (Under Review) [arxiv]

  8. Kushal Bose. “Rewiring with Parallel Edges: An Analysis through the Lens of Graph Spectrum”. (Under Review)

  9. Kushal Bose. “On Connection between CLS Token and Virtual Node: Are they both sides of the same coin?”. (Under Review)

  10. Indronil Ojha, Kushal Bose, and Swagatam Das. “AffNet: Designing Multi-headed Affinity and Adaptive Thresholding for Efficient Link Prediction”. (Under Revision)

  11. Aniruddha Mandal, Kushal Bose, and Swagatam Das. “Revisiting Oversquashing in Graph Neural Networks: A Memory-augmented Message Passing Approach”. (Under Review)

  12. Sujoy Nath, Arkaprabha Basu, Kushal Bose, and Swagatam Das. “From Complexity to Clarity: Transforming Chest X-ray Reports with Chained Prompting (Student Abstract)”. In Association for the Advancement of Artificial Intelligence, 2025 (AAAI). [paper]

  13. Supratik Sarkar, Kushal Bose, and Swagatam Das. “Proof-Carrying Generation: Externally Verifiable Multi-Agent Systems”. (Under Review).

  14. Sagar Ghosh, Kushal Bose, and Swagatam Das. “Transformers Are Universally Consistent: A Sequence-to-Sequence Regression Estimation Perspective”. (Under Review) [arxiv]

  15. Sagar Ghosh, Kushal Bose, and Swagatam Das. “On the universal statistical consistency of expansive hyperbolic deep convolutional neural networks”. (Under Revision) [arxiv]

  16. Arghya Pratihar, Kushal Bose, and Swagatam Das. “Topology-Driven Clustering: Enhancing Performance with Betti Number Filtration”. (Under Review) [arxiv]

  17. Arkaprabha Basu, Kushal Bose, Sankha Subhra Mullick, Anish Chakrabarty, Swagatam Das. “Fortifying fully convolutional generative adversarial networks for image super-resolution using divergence measures”. (Under Revision) [arxiv]

  18. Shubhayan Pan, Saptarshi Chakraborty, Debolina Paul, Kushal Bose, Swagatam Das. “Kernelizing Convex Clustering: A Study on Convergence, Finite Sample Bounds, and Performance Insights”. (Under Review) [arxiv]