12 papers
Linear Strategic Classification with Endogenous Improvements
Siddharth Shrivastava, Mahvith Akshintala, B Vamsha Vardhan Reddy +3
Strategic classification studies settings in which agents respond to a deployed classifier by modifying observable features at a cost. Classical models typically treat such respons…
Training-Free Cross-Architecture Merging for Graph Neural Networks
Rishabh Bhattacharya, Vikaskumar Kalsariya, Naresh Manwani
Model merging has emerged as a powerful paradigm for combining the capabilities of distinct expert models without the high computational cost of retraining, yet current methods are…
EdgeMask-DG*: Learning Domain-Invariant Graph Structures via Adversarial Edge Masking
Rishabh Bhattacharya, Naresh Manwani
Structural shifts pose a significant challenge for graph neural networks, as graph topology acts as a covariate that can vary across domains. Existing domain generalization methods…
DFORD: Directional Feedback based Online Ordinal Regression Learning
Naresh Manwani, M Elamparithy, Tanish Taneja
In this paper, we introduce directional feedback in the ordinal regression setting, in which the learner receives feedback on whether the predicted label is on the left or the righ…
Robust Object Detection with Pseudo Labels from VLMs using Per-Object Co-teaching
Uday Bhaskar, Rishabh Bhattacharya, Avinash Patel +3
Foundation models, especially vision-language models (VLMs), offer compelling zero-shot object detection for applications like autonomous driving, a domain where manual labelling i…
Pseudo-labelling meets Label Smoothing for Noisy Partial Label Learning
Darshana Saravanan, Naresh Manwani, Vineet Gandhi
We motivate weakly supervised learning as an effective learning paradigm for problems where curating perfectly annotated datasets is expensive and may require domain expertise such…