Author

H. Harikumar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

Similarity-Aware Machine Unlearning

This work introduces a retain-aware localization method that considers parameter importance to both forgotten and retained data, and introduces a retain-similar evaluation set, constructed using cosine similarity in the model embedding space, to directly measure collateral damage.

M. Kumaran, M. P. Unni, Vicky Kouni et al. · 0 citations