Robust Multi-Task Learning with t-Pro cesses
Shipeng Yu - CAD and Knowledge Solutions, Siemens Medical Solutions, USA
Volker Tresp - Corporate Technology, Siemens AG, Germany
Kai Yu - NEC Lab America, USA
Most current multi-task learning frameworks ignore the robustness issue, which means that the presence of "outlier" tasks may greatly reduce overall system performance. We introduce a robust framework for Bayesian multitask learning, t-processes (TP), which are a generalization of Gaussian processes (GP) for multi-task learning. TP allows the system to effectively distinguish good tasks from noisy or outlier tasks. Experiments show that TP not only improves overall system performance, but can also serve as an indicator for the "informativeness" of different tasks.