9 citations · 14 across the 7 of their papers we have counts for
3 papers · 1 filter
Perturbing the Gradient for Alleviating Meta Overfitting
Manas Gogoi, Sambhavi Tiwari, Shekhar Verma
The reason for Meta Overfitting can be attributed to two factors: Mutual Non-exclusivity and the Lack of diversity, consequent to which a single global function can fit the support…
FAM: fast adaptive federated meta-learning
Indrajeet Kumar Sinha, Shekhar Verma, Krishna Pratap Singh
In this work, we propose a fast adaptive federated meta-learning (FAM) framework for collaboratively learning a single global model, which can then be personalized locally on indiv…
Learning to Learn with Indispensable Connections
Sambhavi Tiwari, Manas Gogoi, Shekhar Verma +1
Meta-learning aims to solve unseen tasks with few labelled instances. Nevertheless, despite its effectiveness for quick learning in existing optimization-based methods, it has seve…