Rodolphe Jenatton, Mark Collier, Jesse Berent, Alexander D'amour, Guillermo Ortiz-Jimenez, Anant Nawalgaria, Effrosyni Kokiopoulou
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Leveraging privileged information (PI), or features available during training but not at test time, has recently been shown to be an effective method for addressing label noise. However, the reasons for its effectiveness are not well understood. In this study, we investigate the role played by different properties of the PI in explaining away label noise. Through experiments on multiple datasets with real PI (CIFAR-N/H) and a new large-scale benchmark ImageNet-PI, we find that PI is most helpful when it allows networks to easily distinguish clean from mislabeled data, while enabling a learning shortcut to memorize the mislabeled examples. Interestingly, when PI becomes too predictive of the target label, PI methods often perform worse than their no-PI baselines. Based on these findings, we propose several enhancements to the state-of-the-art PI methods and demonstrate the potential of PI as a means of tackling label noise. Finally, we show how we can easily combine the resulting PI approaches with existing no-PI techniques designed to deal with label noise.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.01806")
get_code_for_paper("2303.01806")
have("2303.01806")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2303.01806.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2303.01806)
Connect an agent — have() is free.