Kushal Bose (He/Him)

Kushal Bose (He/Him)

Researcher of GNN and Hyperbolic spaces

Publication

  1. Ojha Indronil, Bose Kushal, and Swagatam Das. “FairSplit: Mitigating Bias in Graph Neural Networks through Sensitivity-based Edge Partitioning” to be presented in ACM CIKM 2025.
  2. Bose, Kushal, Saptarshi Banerjee, and Swagatam Das. “Can Graph Neural Networks Tackle Heterophily? Yes, With a Label-Guided Graph Rewiring Approach!.” IEEE Transactions on Neural Networks and Learning Systems (2025).
  3. Nath, Sujoy, et al. “From Complexity to Clarity: Transforming Chest X-ray Reports with Chained Prompting (Student Abstract).” Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 39. No. 28. 2025.
  4. Ojha, Indranil, Kushal Bose, and Swagatam Das. “Affinity-based homophily: Can we measure homophily of a graph without using node labels?.” The Second Tiny Papers Track at ICLR 2024.
  5. Bose, Kushal, and Swagatam Das. “Can graph neural networks go deeper without over-smoothing? Yes, with a randomized path exploration!.” IEEE Transactions on Emerging Topics in Computational Intelligence 7.5 (2023): 1595-1604.
  6. Bose, Kushal, and Swagatam Das. “HyPE-GT: where Graph Transformers meet Hyperbolic Positional Encodings.” arXiv preprint arXiv:2312.06576 (2023).
  7. Ghosh, Sagar, Kushal Bose, and Swagatam Das. “Transformers Are Universally Consistent.” arXiv preprint arXiv:2505.24531 (2025).
  8. Pratihar, Arghya, Kushal Bose, and Swagatam Das. “Topology-Driven Clustering: Enhancing Performance with Betti Number Filtration.” arXiv preprint arXiv:2505.04346 (2025).
  9. Ghosh, Sagar, Kushal Bose, and Swagatam Das. “On the universal statistical consistency of expansive hyperbolic deep convolutional neural networks.” arXiv preprint arXiv:2411.10128 (2024).
  10. Basu, Arkaprabha, et al. “Fortifying fully convolutional generative adversarial networks for image super-resolution using divergence measures.” arXiv preprint arXiv:2404.06294 (2024).