Learning Federated Representations and Recommendations with Limited Negatives

Understand

Deep retrieval models are widely used for learning entity representations and recommendations.

• Federated learning provides a privacy-preserving way to train these models without requiring centralization of user data.
• However, federated deep retrieval models usually perform much worse than their centralized counterparts due to non-IID (independent and identically distributed) training data on clients, an intrinsic property of federated learning that limits negatives available for training.
• We demonstrate that this issue is distinct from the commonly studied client drift problem.