Towards Interpretable Multi-Task Learning Using Bilevel Programming
arXiv:2009.05483
Abstract
Interpretable Multi-Task Learning can be expressed as learning a sparse graph of the task relationship based on the prediction performance of the learned models. Since many natural phenomenon exhibit sparse structures, enforcing sparsity on learned models reveals the underlying task relationship. Moreover, different sparsification degrees from a fully connected graph uncover various types of structures, like cliques, trees, lines, clusters or fully disconnected graphs. In this paper, we propose a bilevel formulation of multi-task learning that induces sparse graphs, thus, revealing the underlying task relationships, and an efficient method for its computation. We show empirically how the induced sparse graph improves the interpretability of the learned models and their relationship on synthetic and real data, without sacrificing generalization performance. Code at https://bit.ly/GraphGuidedMTL
arXiv commentManuscript accepted at ECML PKDD 2020
References in corpus (8)
- A Unified Approach to Interpreting Model Predictions
- An Overview of Multi-Task Learning in Deep Neural Networks
- A Survey on Multi-Task Learning
- "Why Should I Trust You?": Explaining the Predictions of Any Classifier
- Bilevel Programming for Hyperparameter Optimization and Meta-Learning
- Sparse Signal Recovery via Generalized Entropy Functions Minimization
- Multi-task Sparse Structure Learning
- Multi-task Learning over Graph Structures