Bayesian Multitask Learning with Latent Hierarchies

Abstract

We learn multiple hypotheses for related tasks under a latent hierarchical relationship between tasks. We exploit the intuition that for domain adaptation, we wish to share classifier structure, but for multitask learning, we wish to share covariance structure. Our hierarchical model is seen to subsume several previously proposed multitask learning models and performs well on three distinct real-world data sets.

References in corpus (2)

• Frustratingly Easy Domain Adaptation
• Bayesian Agglomerative Clustering with Coalescents

Cited by in corpus (5)

• Multi-Task Learning for Dense Prediction Tasks: A Survey
• A Convex Formulation for Learning Task Relationships in Multi-Task Learning
• Configurable 3D Scene Synthesis and 2D Image Rendering with Per-Pixel Ground Truth using Stochastic Grammars
• TPG-DNN: A Method for User Intent Prediction Based on Total Probability Formula and GRU Loss with Multi-task Learning
• Multi-Task Neural Processes