Learning an Interpretable Graph Structure in Multi-Task Learning

TL;DR

This paper introduces a method that jointly learns task relationships and models in multi-task learning, producing an interpretable, sparse graph that enhances understanding and reduces errors.

Contribution

The novel approach simultaneously learns task relationships and models without prior graph assumptions, extending to nonlinear forms with RBFN.

Findings

Reduces generalization error compared to state-of-the-art methods

Learns a sparse, interpretable task relationship graph

Effective on both synthetic and real-world data

Abstract

We present a novel methodology to jointly perform multi-task learning and infer intrinsic relationship among tasks by an interpretable and sparse graph. Unlike existing multi-task learning methodologies, the graph structure is not assumed to be known a priori or estimated separately in a preprocessing step. Instead, our graph is learned simultaneously with model parameters of each task, thus it reflects the critical relationship among tasks in the specific prediction problem. We characterize graph structure with its weighted adjacency matrix and show that the overall objective can be optimized alternatively until convergence. We also show that our methodology can be simply extended to a nonlinear form by being embedded into a multi-head radial basis function network (RBFN). Extensive experiments, against six state-of-the-art methodologies, on both synthetic data and real-world applications suggest that our methodology is able to reduce generalization error, and, at the same time, reveal a sparse graph over tasks that is much easier to interpret.