Inductive Learning
SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Training
We propose SemiFL to address the problem of combining communication-efficient FL such as FedAvg with Semi-Supervised Learning (SSL).
A Proofs
This is essentially by definition--intervention on Z doesn't change the potential outcomes, so it doesn't change the value of f (X). If f is a counterfactually invariant predictor: 1. Let L be either square error or cross entropy loss. Suppose that the target distribution Q is causally compatible with the training distribution P . Suppose that any of the following conditions hold: 1. the data obeys the anti-causal graph 2. the data obeys the causal-direction graph, there is no confounding (but possibly selection), and the association is purely spurious, Y X | X We begin with the anti-causal case.
Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation
Open-Set Domain Adaptation (OSDA) assumes that a target domain contains unknown classes, which are not discovered in a source domain.
Data driven semi-supervised learning
We obtain low regret and efficient algorithms in the online setting, and generalization guarantees in the distributional setting.
