Auxiliary Task Reweighting for Minimum-data Learning
arXiv:2010.08244
Abstract
Supervised learning requires a large amount of training data, limiting its application where labeled data is scarce. To compensate for data scarcity, one possible method is to utilize auxiliary tasks to provide additional supervision for the main task. Assigning and optimizing the importance weights for different auxiliary tasks remains an crucial and largely understudied research question. In this work, we propose a method to automatically reweight auxiliary tasks in order to reduce the data requirement on the main task. Specifically, we formulate the weighted likelihood function of auxiliary tasks as a surrogate prior for the main task. By adjusting the auxiliary task weights to minimize the divergence between the surrogate prior and the true prior of the main task, we obtain a more accurate prior estimation, achieving the goal of minimizing the required amount of training data for the main task and avoiding a costly grid search. In multiple experimental settings (e.g. semi-supervised learning, multi-label classification), we demonstrate that our algorithm can effectively utilize limited labeled data of the main task with the benefit of auxiliary tasks compared with previous task reweighting methods. We also show that under extreme cases with only a few extra examples (e.g. few-shot domain adaptation), our algorithm results in significant improvement over the baseline.
arXiv commentNeurIPS 2020. Project page: https://sites.google.com/view/auxiliary-task-reweighting/home
References in corpus (15)
- Adam: A Method for Stochastic Optimization
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- A Simple Framework for Contrastive Learning of Visual Representations
- Improved Regularization of Convolutional Neural Networks with Cutout
- An Overview of Multi-Task Learning in Deep Neural Networks
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Temporal Ensembling for Semi-Supervised Learning
- GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
- Multi-Task Learning as Multi-Objective Optimization
- Learning Multiple Tasks with Multilinear Relationship Networks
- A Closer Look at Few-shot Classification
- Loss is its own Reward: Self-Supervision for Reinforcement Learning
- Adapting Auxiliary Losses Using Gradient Similarity
- Towards Shape Biased Unsupervised Representation Learning for Domain Generalization
- Stein Neural Sampler