AANG: Automating Auxiliary Learning

• URL: http://arxiv.org/abs/2205.14082v1
• Date: Fri, 27 May 2022 16:32:28 GMT
• Title: AANG: Automating Auxiliary Learning
• Authors: Lucio M. Dery, Paul Michel, Mikhail Khodak, Graham Neubig and Ameet Talwalkar
• Abstract summary: We present an approach for automatically generating a suite of auxiliary objectives. We achieve this by deconstructing existing objectives within a novel unified taxonomy, identifying connections between them, and generating new ones based on the uncovered structure. This leads us to a principled and efficient algorithm for searching the space of generated objectives to find those most useful to a specified end-task.
• Score: 110.36191309793135
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When faced with data-starved or highly complex end-tasks, it is commonplace for machine learning practitioners to introduce auxiliary objectives as supplementary learning signals. Whilst much work has been done to formulate useful auxiliary objectives, their construction is still an art which proceeds by slow and tedious hand-design. Intuitions about how and when these objectives improve end-task performance have also had limited theoretical backing. In this work, we present an approach for automatically generating a suite of auxiliary objectives. We achieve this by deconstructing existing objectives within a novel unified taxonomy, identifying connections between them, and generating new ones based on the uncovered structure. Next, we theoretically formalize widely-held intuitions about how auxiliary learning improves generalization of the end-task. This leads us to a principled and efficient algorithm for searching the space of generated objectives to find those most useful to a specified end-task. With natural language processing (NLP) as our domain of study, we empirically verify that our automated auxiliary learning pipeline leads to strong improvements over competitive baselines across continued training experiments on a pre-trained model on 5 NLP end-tasks.

Related papers

• Discovering Temporally-Aware Reinforcement Learning Algorithms [42.016150906831776]
  We propose a simple augmentation to two existing objective discovery approaches. We find that commonly used meta-gradient approaches fail to discover adaptive objective functions.
  arXiv  Detail & Related papers  (2024-02-08T17:07:42Z)
• Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks [33.98624423578388]
  Auxiliary tasks improve representations learned by deep reinforcement learning agents. We derive a new family of auxiliary tasks based on the successor measure. We show that proto-value networks produce rich features that may be used to obtain performance comparable to established algorithms.
  arXiv  Detail & Related papers  (2023-04-25T04:25:08Z)
• Exploiting Contextual Structure to Generate Useful Auxiliary Tasks [12.236546713167945]
  Reinforcement learning requires interaction with an environment, which is expensive for robots. We propose an approach that maximizes experience reuse while learning to solve a given task by generating and simultaneously learning useful auxiliary tasks.
  arXiv  Detail & Related papers  (2023-03-09T05:11:30Z)
• Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning [99.38163119531745]
  We show that applying a discretizing bottleneck can improve performance in goal-conditioned RL setups. We experimentally prove the expected return on out-of-distribution goals, while still allowing for specifying goals with expressive structure.
  arXiv  Detail & Related papers  (2022-11-01T03:31:43Z)
• Auxiliary task discovery through generate-and-test [7.800263769988046]
  Auxiliary tasks improve data efficiency by forcing the agent to learn auxiliary prediction and control objectives. In this paper, we explore an approach to auxiliary task discovery in reinforcement learning based on ideas from representation learning. We introduce a new measure of auxiliary tasks' usefulness based on how useful the features induced by them are for the main task.
  arXiv  Detail & Related papers  (2022-10-25T22:04:37Z)
• Composite Learning for Robust and Effective Dense Predictions [81.2055761433725]
  Multi-task learning promises better model generalization on a target task by jointly optimizing it with an auxiliary task. We find that jointly training a dense prediction (target) task with a self-supervised (auxiliary) task can consistently improve the performance of the target task, while eliminating the need for labeling auxiliary tasks.
  arXiv  Detail & Related papers  (2022-10-13T17:59:16Z)
• Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative [88.11465517304515]
  In general, the pre-training step relies on little to no direct knowledge of the task on which the model will be fine-tuned. We show that multi-tasking the end-task and auxiliary objectives results in significantly better downstream task performance.
  arXiv  Detail & Related papers  (2021-09-15T17:13:18Z)
• Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation [87.1188556802942]
  We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. We propose a novel Cross-Task Relation Layer (CTRL), which encodes task dependencies between the semantic and depth predictions. Furthermore, we propose an Iterative Self-Learning (ISL) training scheme, which exploits semantic pseudo-labels to provide extra supervision on the target domain.
  arXiv  Detail & Related papers  (2021-05-17T13:42:09Z)
• Auxiliary Learning by Implicit Differentiation [54.92146615836611]
  Training neural networks with auxiliary tasks is a common practice for improving the performance on a main task of interest. Here, we propose a novel framework, AuxiLearn, that targets both challenges based on implicit differentiation. First, when useful auxiliaries are known, we propose learning a network that combines all losses into a single coherent objective function. Second, when no useful auxiliary task is known, we describe how to learn a network that generates a meaningful, novel auxiliary task.
  arXiv  Detail & Related papers  (2020-06-22T19:35:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.