Unverified50% confidenceFactExact time
Google first applied federated learning to next-word prediction in the Android keyboard, and Apple applied it to personalization improvements in Siri.
1
Sources
50%
Confidence
Long-term
Relevance
8/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGoogle has applied Federated Learning technology to Gboard keyboard prediction.76% similarUnverifiedFederated learning was proposed by Google in 2016, originally to address privacy issues in model training on mobile devices.71% similarUnverifiedThe new Siri has been completely rebuilt through a partnership with Google, incorporating Gemini as one of the underlying large language models within the Apple Intelligence framework.66% similarUnverified谷歌通过多任务学习框架，将点击率预估与风格偏好建模联合训练，实现二手稀缺品类的个性化推荐65% similarVerifiedFederated learning is a distributed machine learning paradigm proposed by Google in 2017, allowing models to be trained on local devices without uploading raw data to a central server.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/832848API
curl https://kongchang.com/api/v1/knowledge/claims/832848MCP
get_claim(id=832848)