157 citations · 233 across the 11 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021★ 11 cited
Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance
Shibal Ibrahim, Natalia Ponomareva, Rahul Mazumder
Fine-tuning of large pre-trained image and language models on small customized datasets has become increasingly popular for improved prediction and efficient use of limited resourc…
cs.LG2021★ 22 cited
Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data
Qi Zhu, Natalia Ponomareva, Jiawei Han +1
There has been a recent surge of interest in designing Graph Neural Networks (GNNs) for semi-supervised learning tasks. Unfortunately this work has assumed that the nodes labeled f…