Federated Learning Of Out-Of-Vocabulary Words — mentioned by ximeng

Sat, 18 May 2019 05:20:35 GMT

Linked paper on using this for Google Keyboard (https://arxiv.org/pdf/1903.10635.pdf) highlights that there are nevertheless still privacy issues with this approach: While Federated Learning removes the need to upload raw user material — here OOV words — to the server, the privacy risk of unintended memorization still exists (as demonstrated in (Carlini et al., 2018)). Such risk can be mitigated, usually with some accuracy cost, using techniques including differential privacy (McMahan et al., 2018). Exploring these trade-offs is beyond the scope of this paper.

Paper and discussion history. A mention is not an endorsement.

Federated Learning Of Out-Of-Vocabulary Words · HackerPapers discussions

Federated Learning Of Out-Of-Vocabulary Words — mentioned by ximeng